diff --git a/.RData b/.RData
new file mode 100644
index 0000000000000000000000000000000000000000..9c336843e114fae92577008ad8b421342d4d6e61
Binary files /dev/null and b/.RData differ
diff --git a/R/sim_all.R b/R/sim_all.R
index 94830bf5478e884ab2eea3a0c7c876fcbfce4b44..9d6b6b7fb43311f94dca6003b6427c22fb8c9fe4 100644
--- a/R/sim_all.R
+++ b/R/sim_all.R
@@ -1,11 +1,11 @@
#' Is a wrapper for sim_choice executing the simulation over all designs stored in a specific folder
-#'
+#' update
#' @param nosim Number of runs or simulations. For testing use 2 but once you go serious, use at least 200, for better results use 2000.
#' @param resps Number of respondents you want to simulate
#' @param destype Is it a design created with ngene or with spdesign. Ngene desings should be stored as the standard .ngd output. spdesign should be the spdesign object design$design
#' @param designpath The path to the folder where the designs are stored. For example "c:/myfancydec/Designs"
-#' @param u A list with utility functions. The list can incorporate as many decision rule groups as you want. However, each group must be in a list in this list. If you just use one group (the normal), this group still has to be in a list in the u list.
-#' @param bcoefficients List of coefficients for the utility function. List content/length can vary based on application, but item names should be in namespace: {bsq, bredkite, bdistance, bcost, bfarm2, bfarm3, bheight2, bheight3}
+#' @param u A list with utility functions. The list can incorporate as many decision rule groups as you want. However, each group must be in a list in this list. If you just use one group (the normal), this group still has to be in a list in the u list. As a convention name beta coefficients starting with a lower case "b"
+#' @param bcoefficients List of initial coefficients for the utility function. List content/length can vary based on application, but should all begin with b and be the same as those entered in the utility functions
#'
#' @return A list, with all information on the simulation. This list an be easily processed by the user and in the rmarkdown template.
#' @export
@@ -27,21 +27,61 @@
#'
sim_all <- function(nosim=2, resps, destype="ngene", designpath, u, bcoeff){
+ #################################################
+ ########## Input Validation Test ###############
+ #################################################
-
+ ########### validate the utility function ########
if (missing(u) || !(is.list(u) && any(sapply(u, is.list)))){
- stop(" 'u' must be provided and must be a list containing at least one list element.")
+ stop(" 'u' must be provided and must be a list containing at least one list element (list of lists).")
+ }
+
+ ########## validate the bcoeff list ################
+ # Check if bcoeff is provided
+ if (missing(bcoeff)) {
+ stop("Argument 'bcoeff' is required.")
+ }
+
+ # Check if bcoeff is a list
+ if (!is.list(bcoeff)) {
+ stop("Argument 'bcoeff' must be a list.")
}
+ # Check if values in bcoeff are numeric
+ if (!all(sapply(bcoeff, is.numeric))) {
+ stop("Values in 'bcoeff' must be numeric.")
+ }
+
+ #### check that all the coefficients in utility function have a cooresponding value in bcoeff ####
+ # Extract coefficients from utility function starting with "b"
+ coeff_names_ul <- unique(unlist(lapply(u, function(u) {
+ formula_strings <- unlist(u)
+ coef_names <- unique(unlist(lapply(formula_strings, function(f) {
+ # Parse the formula to extract coefficient names
+ all_vars <- all.vars(as.formula(f))
+ coef_vars <- all_vars[grep("^b", all_vars)]
+ return(coef_vars)
+ })))
+ return(coef_names)
+ })))
+
+ # Check if all utility function coefficients starting with "b" are covered in bcoeff list
+ missing_coeffs <- coeff_names_ul[!(coeff_names_ul %in% names(bcoeff))]
+ if (length(missing_coeffs) > 0) {
+ stop(paste("Missing coefficients in 'bcoeff':", paste(missing_coeffs, collapse = ", "), ". Perhaps there is a typo?"))
+ }
+ ########## validate resps #####################
if (missing(resps) || !(is.integer(resps) || (is.numeric(resps) && identical(trunc(resps), resps)))) {
stop(" 'resps' must be provided and must be an integer indicating the number of respondents per run.")
}
-
+ ########## validate designpath ################
if (!dir.exists(designpath)) {
stop(" The folder where your designs are stored does not exist. \n Check if designpath is correctly specified")
}
-
+ #################################################
+ ########## End Validation Tests #################
+ #################################################
designfile<-list.files(designpath,full.names = T)
designname <- stringr::str_remove_all(list.files(designpath,full.names = F),
diff --git a/R/simulate_choices.R b/R/simulate_choices.R
index 8b7c75b6e8607bec46001ecbb4069be295f05213..4066d356b1f850eac8166ab1bf4e240c822f2a05 100644
--- a/R/simulate_choices.R
+++ b/R/simulate_choices.R
@@ -9,6 +9,7 @@
#'
#' @examples \dontrun{simulate_choices(datadet, ut,setspp)}
simulate_choices <- function(data, utility, setspp, destype, bcoefficients) { #the part in dataset that needs to be repeated in each run
+<<<<<<< HEAD
### unpack the bcoeff list
bsq <- bcoefficients$bsq
@@ -19,6 +20,12 @@ simulate_choices <- function(data, utility, setspp, destype, bcoefficients) { #
bfarm3 <- bcoefficients$bfarm3
bheight2 <- bcoefficients$bheight2
bheight3 <- bcoefficients$bheight3
+=======
+ ### unpack the bcoeff list so variables are accessible
+ for (key in names(bcoefficients)) {
+ assign(key, bcoefficients[[key]])
+ }
+>>>>>>> 0c1de67f1d4f2236d97e706a4b99a89bdba8a0b3
diff --git a/README.Rmd b/README.Rmd
index 2c8baae3fb66bd1c43f24efadef94428206ec9a8..ddecc87272348fe6ec7912617c216e15c740ca7d 100644
--- a/README.Rmd
+++ b/README.Rmd
@@ -19,7 +19,7 @@ knitr::opts_chunk$set(
<!-- badges: end -->
-The goal of simulateDCE is to make it easy to simulate choice experiment datasets using designs from NGENE or `spdesign`. You have to store the design file in a subfolder and need to specify certain parameters and the utility functions for the data generating process. The package is useful for
+The goal of simulateDCE is to make it easy to simulate choice experiment datasets using designs from NGENE or `spdesign`. You have to store the design file in a subfolder and need to specify certain parameters and the utility functions for the data generating process. The package is useful for:
1. Test different designs in terms of statistical power, efficiency and unbiasedness
@@ -66,16 +66,17 @@ nosim= 2 # number of simulations to run (about 500 is minimum)
-# bpreis = -0.036
-# blade = -0.034
-# bwarte = -0.049
+# bcoeff <- list(
+# bpreis = -0.036,
+# blade = -0.034,
+# bwarte = -0.049)
decisiongroups=c(0,0.7,1)
# wrong parameters
-#
+# place b coefficients into an r list:
bcoeff = list(
bpreis = -0.01,
blade = -0.07,
diff --git a/README.html b/README.html
new file mode 100644
index 0000000000000000000000000000000000000000..693b6d348258fd09e62476844730cc11a3aba3b6
--- /dev/null
+++ b/README.html
@@ -0,0 +1,1487 @@
+<!DOCTYPE html>
+
+<html xmlns="http://www.w3.org/1999/xhtml">
+
+<head>
+
+<meta charset="utf-8">
+<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+<meta name="generator" content="pandoc" />
+<meta name="viewport" content="width=device-width, initial-scale=1">
+
+<style type="text/css">
+@font-face {
+font-family: octicons-link;
+src: url(data:font/woff;charset=utf-8;base64,d09GRgABAAAAAAZwABAAAAAACFQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABEU0lHAAAGaAAAAAgAAAAIAAAAAUdTVUIAAAZcAAAACgAAAAoAAQAAT1MvMgAAAyQAAABJAAAAYFYEU3RjbWFwAAADcAAAAEUAAACAAJThvmN2dCAAAATkAAAABAAAAAQAAAAAZnBnbQAAA7gAAACyAAABCUM+8IhnYXNwAAAGTAAAABAAAAAQABoAI2dseWYAAAFsAAABPAAAAZwcEq9taGVhZAAAAsgAAAA0AAAANgh4a91oaGVhAAADCAAAABoAAAAkCA8DRGhtdHgAAAL8AAAADAAAAAwGAACfbG9jYQAAAsAAAAAIAAAACABiATBtYXhwAAACqAAAABgAAAAgAA8ASm5hbWUAAAToAAABQgAAAlXu73sOcG9zdAAABiwAAAAeAAAAME3QpOBwcmVwAAAEbAAAAHYAAAB/aFGpk3jaTY6xa8JAGMW/O62BDi0tJLYQincXEypYIiGJjSgHniQ6umTsUEyLm5BV6NDBP8Tpts6F0v+k/0an2i+itHDw3v2+9+DBKTzsJNnWJNTgHEy4BgG3EMI9DCEDOGEXzDADU5hBKMIgNPZqoD3SilVaXZCER3/I7AtxEJLtzzuZfI+VVkprxTlXShWKb3TBecG11rwoNlmmn1P2WYcJczl32etSpKnziC7lQyWe1smVPy/Lt7Kc+0vWY/gAgIIEqAN9we0pwKXreiMasxvabDQMM4riO+qxM2ogwDGOZTXxwxDiycQIcoYFBLj5K3EIaSctAq2kTYiw+ymhce7vwM9jSqO8JyVd5RH9gyTt2+J/yUmYlIR0s04n6+7Vm1ozezUeLEaUjhaDSuXHwVRgvLJn1tQ7xiuVv/ocTRF42mNgZGBgYGbwZOBiAAFGJBIMAAizAFoAAABiAGIAznjaY2BkYGAA4in8zwXi+W2+MjCzMIDApSwvXzC97Z4Ig8N/BxYGZgcgl52BCSQKAA3jCV8CAABfAAAAAAQAAEB42mNgZGBg4f3vACQZQABIMjKgAmYAKEgBXgAAeNpjYGY6wTiBgZWBg2kmUxoDA4MPhGZMYzBi1AHygVLYQUCaawqDA4PChxhmh/8ODDEsvAwHgMKMIDnGL0x7gJQCAwMAJd4MFwAAAHjaY2BgYGaA4DAGRgYQkAHyGMF8NgYrIM3JIAGVYYDT+AEjAwuDFpBmA9KMDEwMCh9i/v8H8sH0/4dQc1iAmAkALaUKLgAAAHjaTY9LDsIgEIbtgqHUPpDi3gPoBVyRTmTddOmqTXThEXqrob2gQ1FjwpDvfwCBdmdXC5AVKFu3e5MfNFJ29KTQT48Ob9/lqYwOGZxeUelN2U2R6+cArgtCJpauW7UQBqnFkUsjAY/kOU1cP+DAgvxwn1chZDwUbd6CFimGXwzwF6tPbFIcjEl+vvmM/byA48e6tWrKArm4ZJlCbdsrxksL1AwWn/yBSJKpYbq8AXaaTb8AAHja28jAwOC00ZrBeQNDQOWO//sdBBgYGRiYWYAEELEwMTE4uzo5Zzo5b2BxdnFOcALxNjA6b2ByTswC8jYwg0VlNuoCTWAMqNzMzsoK1rEhNqByEyerg5PMJlYuVueETKcd/89uBpnpvIEVomeHLoMsAAe1Id4AAAAAAAB42oWQT07CQBTGv0JBhagk7HQzKxca2sJCE1hDt4QF+9JOS0nbaaYDCQfwCJ7Au3AHj+LO13FMmm6cl7785vven0kBjHCBhfpYuNa5Ph1c0e2Xu3jEvWG7UdPDLZ4N92nOm+EBXuAbHmIMSRMs+4aUEd4Nd3CHD8NdvOLTsA2GL8M9PODbcL+hD7C1xoaHeLJSEao0FEW14ckxC+TU8TxvsY6X0eLPmRhry2WVioLpkrbp84LLQPGI7c6sOiUzpWIWS5GzlSgUzzLBSikOPFTOXqly7rqx0Z1Q5BAIoZBSFihQYQOOBEdkCOgXTOHA07HAGjGWiIjaPZNW13/+lm6S9FT7rLHFJ6fQbkATOG1j2OFMucKJJsxIVfQORl+9Jyda6Sl1dUYhSCm1dyClfoeDve4qMYdLEbfqHf3O/AdDumsjAAB42mNgYoAAZQYjBmyAGYQZmdhL8zLdDEydARfoAqIAAAABAAMABwAKABMAB///AA8AAQAAAAAAAAAAAAAAAAABAAAAAA==) format('woff');
+}
+body {
+-webkit-text-size-adjust: 100%;
+text-size-adjust: 100%;
+color: #333;
+font-family: "Helvetica Neue", Helvetica, "Segoe UI", Arial, freesans, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol";
+font-size: 16px;
+line-height: 1.6;
+word-wrap: break-word;
+}
+a {
+background-color: transparent;
+}
+a:active,
+a:hover {
+outline: 0;
+}
+strong {
+font-weight: bold;
+}
+h1 {
+font-size: 2em;
+margin: 0.67em 0;
+}
+img {
+border: 0;
+}
+hr {
+box-sizing: content-box;
+height: 0;
+}
+pre {
+overflow: auto;
+}
+code,
+kbd,
+pre {
+font-family: monospace, monospace;
+font-size: 1em;
+}
+input {
+color: inherit;
+font: inherit;
+margin: 0;
+}
+html input[disabled] {
+cursor: default;
+}
+input {
+line-height: normal;
+}
+input[type="checkbox"] {
+box-sizing: border-box;
+padding: 0;
+}
+table {
+border-collapse: collapse;
+border-spacing: 0;
+}
+td,
+th {
+padding: 0;
+}
+* {
+box-sizing: border-box;
+}
+input {
+font: 13px / 1.4 Helvetica, arial, nimbussansl, liberationsans, freesans, clean, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol";
+}
+a {
+color: #4078c0;
+text-decoration: none;
+}
+a:hover,
+a:active {
+text-decoration: underline;
+}
+hr {
+height: 0;
+margin: 15px 0;
+overflow: hidden;
+background: transparent;
+border: 0;
+border-bottom: 1px solid #ddd;
+}
+hr:before {
+display: table;
+content: "";
+}
+hr:after {
+display: table;
+clear: both;
+content: "";
+}
+h1,
+h2,
+h3,
+h4,
+h5,
+h6 {
+margin-top: 15px;
+margin-bottom: 15px;
+line-height: 1.1;
+}
+h1 {
+font-size: 30px;
+}
+h2 {
+font-size: 21px;
+}
+h3 {
+font-size: 16px;
+}
+h4 {
+font-size: 14px;
+}
+h5 {
+font-size: 12px;
+}
+h6 {
+font-size: 11px;
+}
+blockquote {
+margin: 0;
+}
+ul,
+ol {
+padding: 0;
+margin-top: 0;
+margin-bottom: 0;
+}
+ol ol,
+ul ol {
+list-style-type: lower-roman;
+}
+ul ul ol,
+ul ol ol,
+ol ul ol,
+ol ol ol {
+list-style-type: lower-alpha;
+}
+dd {
+margin-left: 0;
+}
+code {
+font-family: Consolas, "Liberation Mono", Menlo, Courier, monospace;
+font-size: 12px;
+}
+pre {
+margin-top: 0;
+margin-bottom: 0;
+font: 12px Consolas, "Liberation Mono", Menlo, Courier, monospace;
+}
+.select::-ms-expand {
+opacity: 0;
+}
+.octicon {
+font: normal normal normal 16px/1 octicons-link;
+display: inline-block;
+text-decoration: none;
+text-rendering: auto;
+-webkit-font-smoothing: antialiased;
+-moz-osx-font-smoothing: grayscale;
+-webkit-user-select: none;
+-moz-user-select: none;
+-ms-user-select: none;
+user-select: none;
+}
+.octicon-link:before {
+content: '\f05c';
+}
+.markdown-body:before {
+display: table;
+content: "";
+}
+.markdown-body:after {
+display: table;
+clear: both;
+content: "";
+}
+.markdown-body>*:first-child {
+margin-top: 0 !important;
+}
+.markdown-body>*:last-child {
+margin-bottom: 0 !important;
+}
+a:not([href]) {
+color: inherit;
+text-decoration: none;
+}
+.anchor {
+display: inline-block;
+padding-right: 2px;
+margin-left: -18px;
+}
+.anchor:focus {
+outline: none;
+}
+h1,
+h2,
+h3,
+h4,
+h5,
+h6 {
+margin-top: 1em;
+margin-bottom: 16px;
+font-weight: bold;
+line-height: 1.4;
+}
+h1 .octicon-link,
+h2 .octicon-link,
+h3 .octicon-link,
+h4 .octicon-link,
+h5 .octicon-link,
+h6 .octicon-link {
+color: #000;
+vertical-align: middle;
+visibility: hidden;
+}
+h1:hover .anchor,
+h2:hover .anchor,
+h3:hover .anchor,
+h4:hover .anchor,
+h5:hover .anchor,
+h6:hover .anchor {
+text-decoration: none;
+}
+h1:hover .anchor .octicon-link,
+h2:hover .anchor .octicon-link,
+h3:hover .anchor .octicon-link,
+h4:hover .anchor .octicon-link,
+h5:hover .anchor .octicon-link,
+h6:hover .anchor .octicon-link {
+visibility: visible;
+}
+h1 {
+padding-bottom: 0.3em;
+font-size: 2.25em;
+line-height: 1.2;
+border-bottom: 1px solid #eee;
+}
+h1 .anchor {
+line-height: 1;
+}
+h2 {
+padding-bottom: 0.3em;
+font-size: 1.75em;
+line-height: 1.225;
+border-bottom: 1px solid #eee;
+}
+h2 .anchor {
+line-height: 1;
+}
+h3 {
+font-size: 1.5em;
+line-height: 1.43;
+}
+h3 .anchor {
+line-height: 1.2;
+}
+h4 {
+font-size: 1.25em;
+}
+h4 .anchor {
+line-height: 1.2;
+}
+h5 {
+font-size: 1em;
+}
+h5 .anchor {
+line-height: 1.1;
+}
+h6 {
+font-size: 1em;
+color: #777;
+}
+h6 .anchor {
+line-height: 1.1;
+}
+p,
+blockquote,
+ul,
+ol,
+dl,
+table,
+pre {
+margin-top: 0;
+margin-bottom: 16px;
+}
+hr {
+height: 4px;
+padding: 0;
+margin: 16px 0;
+background-color: #e7e7e7;
+border: 0 none;
+}
+ul,
+ol {
+padding-left: 2em;
+}
+ul ul,
+ul ol,
+ol ol,
+ol ul {
+margin-top: 0;
+margin-bottom: 0;
+}
+li>p {
+margin-top: 16px;
+}
+dl {
+padding: 0;
+}
+dl dt {
+padding: 0;
+margin-top: 16px;
+font-size: 1em;
+font-style: italic;
+font-weight: bold;
+}
+dl dd {
+padding: 0 16px;
+margin-bottom: 16px;
+}
+blockquote {
+padding: 0 15px;
+color: #777;
+border-left: 4px solid #ddd;
+}
+blockquote>:first-child {
+margin-top: 0;
+}
+blockquote>:last-child {
+margin-bottom: 0;
+}
+table {
+display: block;
+width: 100%;
+overflow: auto;
+word-break: normal;
+word-break: keep-all;
+}
+table th {
+font-weight: bold;
+}
+table th,
+table td {
+padding: 6px 13px;
+border: 1px solid #ddd;
+}
+table tr {
+background-color: #fff;
+border-top: 1px solid #ccc;
+}
+table tr:nth-child(2n) {
+background-color: #f8f8f8;
+}
+img {
+max-width: 100%;
+box-sizing: content-box;
+background-color: #fff;
+}
+code {
+padding: 0;
+padding-top: 0.2em;
+padding-bottom: 0.2em;
+margin: 0;
+font-size: 85%;
+background-color: rgba(0,0,0,0.04);
+border-radius: 3px;
+}
+code:before,
+code:after {
+letter-spacing: -0.2em;
+content: "\00a0";
+}
+pre>code {
+padding: 0;
+margin: 0;
+font-size: 100%;
+word-break: normal;
+white-space: pre;
+background: transparent;
+border: 0;
+}
+.highlight {
+margin-bottom: 16px;
+}
+.highlight pre,
+pre {
+padding: 16px;
+overflow: auto;
+font-size: 85%;
+line-height: 1.45;
+background-color: #f7f7f7;
+border-radius: 3px;
+}
+.highlight pre {
+margin-bottom: 0;
+word-break: normal;
+}
+pre {
+word-wrap: normal;
+}
+pre code {
+display: inline;
+max-width: initial;
+padding: 0;
+margin: 0;
+overflow: initial;
+line-height: inherit;
+word-wrap: normal;
+background-color: transparent;
+border: 0;
+}
+pre code:before,
+pre code:after {
+content: normal;
+}
+kbd {
+display: inline-block;
+padding: 3px 5px;
+font-size: 11px;
+line-height: 10px;
+color: #555;
+vertical-align: middle;
+background-color: #fcfcfc;
+border: solid 1px #ccc;
+border-bottom-color: #bbb;
+border-radius: 3px;
+box-shadow: inset 0 -1px 0 #bbb;
+}
+.pl-c {
+color: #969896;
+}
+.pl-c1,
+.pl-s .pl-v {
+color: #0086b3;
+}
+.pl-e,
+.pl-en {
+color: #795da3;
+}
+.pl-s .pl-s1,
+.pl-smi {
+color: #333;
+}
+.pl-ent {
+color: #63a35c;
+}
+.pl-k {
+color: #a71d5d;
+}
+.pl-pds,
+.pl-s,
+.pl-s .pl-pse .pl-s1,
+.pl-sr,
+.pl-sr .pl-cce,
+.pl-sr .pl-sra,
+.pl-sr .pl-sre {
+color: #183691;
+}
+.pl-v {
+color: #ed6a43;
+}
+.pl-id {
+color: #b52a1d;
+}
+.pl-ii {
+background-color: #b52a1d;
+color: #f8f8f8;
+}
+.pl-sr .pl-cce {
+color: #63a35c;
+font-weight: bold;
+}
+.pl-ml {
+color: #693a17;
+}
+.pl-mh,
+.pl-mh .pl-en,
+.pl-ms {
+color: #1d3e81;
+font-weight: bold;
+}
+.pl-mq {
+color: #008080;
+}
+.pl-mi {
+color: #333;
+font-style: italic;
+}
+.pl-mb {
+color: #333;
+font-weight: bold;
+}
+.pl-md {
+background-color: #ffecec;
+color: #bd2c00;
+}
+.pl-mi1 {
+background-color: #eaffea;
+color: #55a532;
+}
+.pl-mdr {
+color: #795da3;
+font-weight: bold;
+}
+.pl-mo {
+color: #1d3e81;
+}
+kbd {
+display: inline-block;
+padding: 3px 5px;
+font: 11px Consolas, "Liberation Mono", Menlo, Courier, monospace;
+line-height: 10px;
+color: #555;
+vertical-align: middle;
+background-color: #fcfcfc;
+border: solid 1px #ccc;
+border-bottom-color: #bbb;
+border-radius: 3px;
+box-shadow: inset 0 -1px 0 #bbb;
+}
+.task-list-item {
+list-style-type: none;
+}
+.task-list-item+.task-list-item {
+margin-top: 3px;
+}
+.task-list-item input {
+margin: 0 0.35em 0.25em -1.6em;
+vertical-align: middle;
+}
+:checked+.radio-label {
+z-index: 1;
+position: relative;
+border-color: #4078c0;
+}
+.sourceLine {
+display: inline-block;
+}
+code .kw { color: #000000; }
+code .dt { color: #ed6a43; }
+code .dv { color: #009999; }
+code .bn { color: #009999; }
+code .fl { color: #009999; }
+code .ch { color: #009999; }
+code .st { color: #183691; }
+code .co { color: #969896; }
+code .ot { color: #0086b3; }
+code .al { color: #a61717; }
+code .fu { color: #63a35c; }
+code .er { color: #a61717; background-color: #e3d2d2; }
+code .wa { color: #000000; }
+code .cn { color: #008080; }
+code .sc { color: #008080; }
+code .vs { color: #183691; }
+code .ss { color: #183691; }
+code .im { color: #000000; }
+code .va {color: #008080; }
+code .cf { color: #000000; }
+code .op { color: #000000; }
+code .bu { color: #000000; }
+code .ex { color: #000000; }
+code .pp { color: #999999; }
+code .at { color: #008080; }
+code .do { color: #969896; }
+code .an { color: #008080; }
+code .cv { color: #008080; }
+code .in { color: #008080; }
+</style>
+<style>
+body {
+box-sizing: border-box;
+min-width: 200px;
+max-width: 980px;
+margin: 0 auto;
+padding: 45px;
+padding-top: 0px;
+}
+</style>
+
+
+</head>
+
+<body>
+
+<!-- README.md is generated from README.Rmd. Please edit that file -->
+
+<h1 id="simulatedce">simulateDCE</h1>
+<!-- badges: start -->
+
+<!-- badges: end -->
+
+<p>The goal of simulateDCE is to make it easy to simulate choice
+experiment datasets using designs from NGENE or <code>spdesign</code>.
+You have to store the design file in a subfolder and need to specify
+certain parameters and the utility functions for the data generating
+process. The package is useful for:</p>
+<ol style="list-style-type: decimal">
+<li><p>Test different designs in terms of statistical power, efficiency
+and unbiasedness</p></li>
+<li><p>To test the effects of deviations from RUM, e.g. heuristics, on
+model performance for different designs.</p></li>
+<li><p>In teaching, using simulated data is useful, if you want to know
+the data generating process. It helps to demonstrate Maximum likelihood
+and choice models, knowing exactly what you should expect.</p></li>
+<li><p>You can use simulation in pre-registration to justify your sample
+size and design choice.</p></li>
+<li><p>Before data collection, you can use simulated data to estimate
+the models you plan to use in the actual analysis. You can thus make
+sure, you can estimate all effects for given sample sizes.</p></li>
+</ol>
+<h2 id="installation">Installation</h2>
+<p>You can install the development version of simulateDCE from gitlab.
+You need to install the <code>remotes</code> package first. The current
+version is alpha and there is no version on cran:</p>
+<div class="sourceCode" id="cb1"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb1-1"><a href="#cb1-1" tabindex="-1"></a></span>
+<span id="cb1-2"><a href="#cb1-2" tabindex="-1"></a><span class="fu">install.packages</span>(<span class="st">"remotes"</span>)</span>
+<span id="cb1-3"><a href="#cb1-3" tabindex="-1"></a>remotes<span class="sc">::</span><span class="fu">install_gitlab</span>(<span class="at">repo =</span> <span class="st">"dj44vuri/simulateDCE"</span> , <span class="at">host =</span> <span class="st">"https://git.idiv.de"</span>)</span></code></pre></div>
+<h2 id="example">Example</h2>
+<p>This is a basic example for a simulation:</p>
+<div class="sourceCode" id="cb2"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb2-1"><a href="#cb2-1" tabindex="-1"></a></span>
+<span id="cb2-2"><a href="#cb2-2" tabindex="-1"></a></span>
+<span id="cb2-3"><a href="#cb2-3" tabindex="-1"></a><span class="fu">rm</span>(<span class="at">list=</span><span class="fu">ls</span>())</span>
+<span id="cb2-4"><a href="#cb2-4" tabindex="-1"></a><span class="fu">library</span>(simulateDCE)</span>
+<span id="cb2-5"><a href="#cb2-5" tabindex="-1"></a><span class="fu">library</span>(rlang)</span>
+<span id="cb2-6"><a href="#cb2-6" tabindex="-1"></a><span class="fu">library</span>(formula.tools)</span>
+<span id="cb2-7"><a href="#cb2-7" tabindex="-1"></a></span>
+<span id="cb2-8"><a href="#cb2-8" tabindex="-1"></a></span>
+<span id="cb2-9"><a href="#cb2-9" tabindex="-1"></a><span class="fu">library</span>(rlang)</span>
+<span id="cb2-10"><a href="#cb2-10" tabindex="-1"></a></span>
+<span id="cb2-11"><a href="#cb2-11" tabindex="-1"></a>designpath<span class="ot"><-</span> <span class="fu">system.file</span>(<span class="st">"extdata"</span>,<span class="st">"SE_DRIVE"</span> ,<span class="at">package =</span> <span class="st">"simulateDCE"</span>)</span>
+<span id="cb2-12"><a href="#cb2-12" tabindex="-1"></a></span>
+<span id="cb2-13"><a href="#cb2-13" tabindex="-1"></a>resps <span class="ot">=</span><span class="dv">120</span> <span class="co"># number of respondents</span></span>
+<span id="cb2-14"><a href="#cb2-14" tabindex="-1"></a>nosim<span class="ot">=</span> <span class="dv">2</span> <span class="co"># number of simulations to run (about 500 is minimum)</span></span>
+<span id="cb2-15"><a href="#cb2-15" tabindex="-1"></a></span>
+<span id="cb2-16"><a href="#cb2-16" tabindex="-1"></a></span>
+<span id="cb2-17"><a href="#cb2-17" tabindex="-1"></a></span>
+<span id="cb2-18"><a href="#cb2-18" tabindex="-1"></a></span>
+<span id="cb2-19"><a href="#cb2-19" tabindex="-1"></a></span>
+<span id="cb2-20"><a href="#cb2-20" tabindex="-1"></a></span>
+<span id="cb2-21"><a href="#cb2-21" tabindex="-1"></a><span class="co"># bcoeff <- list(</span></span>
+<span id="cb2-22"><a href="#cb2-22" tabindex="-1"></a><span class="co"># bpreis = -0.036,</span></span>
+<span id="cb2-23"><a href="#cb2-23" tabindex="-1"></a><span class="co"># blade = -0.034,</span></span>
+<span id="cb2-24"><a href="#cb2-24" tabindex="-1"></a><span class="co"># bwarte = -0.049)</span></span>
+<span id="cb2-25"><a href="#cb2-25" tabindex="-1"></a></span>
+<span id="cb2-26"><a href="#cb2-26" tabindex="-1"></a></span>
+<span id="cb2-27"><a href="#cb2-27" tabindex="-1"></a>decisiongroups<span class="ot">=</span><span class="fu">c</span>(<span class="dv">0</span>,<span class="fl">0.7</span>,<span class="dv">1</span>)</span>
+<span id="cb2-28"><a href="#cb2-28" tabindex="-1"></a></span>
+<span id="cb2-29"><a href="#cb2-29" tabindex="-1"></a><span class="co"># wrong parameters</span></span>
+<span id="cb2-30"><a href="#cb2-30" tabindex="-1"></a></span>
+<span id="cb2-31"><a href="#cb2-31" tabindex="-1"></a><span class="co"># place b coefficients into an r list:</span></span>
+<span id="cb2-32"><a href="#cb2-32" tabindex="-1"></a>bcoeff <span class="ot">=</span> <span class="fu">list</span>(</span>
+<span id="cb2-33"><a href="#cb2-33" tabindex="-1"></a> <span class="at">bpreis =</span> <span class="sc">-</span><span class="fl">0.01</span>,</span>
+<span id="cb2-34"><a href="#cb2-34" tabindex="-1"></a> <span class="at">blade =</span> <span class="sc">-</span><span class="fl">0.07</span>,</span>
+<span id="cb2-35"><a href="#cb2-35" tabindex="-1"></a> <span class="at">bwarte =</span> <span class="fl">0.02</span>)</span>
+<span id="cb2-36"><a href="#cb2-36" tabindex="-1"></a></span>
+<span id="cb2-37"><a href="#cb2-37" tabindex="-1"></a>manipulations <span class="ot">=</span> <span class="fu">list</span>(<span class="at">alt1.x2=</span> <span class="fu">expr</span>(alt1.x2<span class="sc">/</span><span class="dv">10</span>),</span>
+<span id="cb2-38"><a href="#cb2-38" tabindex="-1"></a> <span class="at">alt1.x3=</span> <span class="fu">expr</span>(alt1.x3<span class="sc">/</span><span class="dv">10</span>),</span>
+<span id="cb2-39"><a href="#cb2-39" tabindex="-1"></a> <span class="at">alt2.x2=</span> <span class="fu">expr</span>(alt2.x2<span class="sc">/</span><span class="dv">10</span>),</span>
+<span id="cb2-40"><a href="#cb2-40" tabindex="-1"></a> <span class="at">alt2.x3=</span> <span class="fu">expr</span>(alt2.x3<span class="sc">/</span><span class="dv">10</span>)</span>
+<span id="cb2-41"><a href="#cb2-41" tabindex="-1"></a>)</span>
+<span id="cb2-42"><a href="#cb2-42" tabindex="-1"></a></span>
+<span id="cb2-43"><a href="#cb2-43" tabindex="-1"></a></span>
+<span id="cb2-44"><a href="#cb2-44" tabindex="-1"></a><span class="co">#place your utility functions here</span></span>
+<span id="cb2-45"><a href="#cb2-45" tabindex="-1"></a>ul<span class="ot"><-</span><span class="fu">list</span>( <span class="at">u1 =</span></span>
+<span id="cb2-46"><a href="#cb2-46" tabindex="-1"></a></span>
+<span id="cb2-47"><a href="#cb2-47" tabindex="-1"></a> <span class="fu">list</span>(</span>
+<span id="cb2-48"><a href="#cb2-48" tabindex="-1"></a> <span class="at">v1 =</span>V<span class="fl">.1</span><span class="sc">~</span> bpreis <span class="sc">*</span> alt1.x1 <span class="sc">+</span> blade<span class="sc">*</span>alt1.x2 <span class="sc">+</span> bwarte<span class="sc">*</span>alt1.x3 ,</span>
+<span id="cb2-49"><a href="#cb2-49" tabindex="-1"></a> <span class="at">v2 =</span>V<span class="fl">.2</span><span class="sc">~</span> bpreis <span class="sc">*</span> alt2.x1 <span class="sc">+</span> blade<span class="sc">*</span>alt2.x2 <span class="sc">+</span> bwarte<span class="sc">*</span>alt2.x3</span>
+<span id="cb2-50"><a href="#cb2-50" tabindex="-1"></a> )</span>
+<span id="cb2-51"><a href="#cb2-51" tabindex="-1"></a></span>
+<span id="cb2-52"><a href="#cb2-52" tabindex="-1"></a> ,</span>
+<span id="cb2-53"><a href="#cb2-53" tabindex="-1"></a> <span class="at">u2 =</span> <span class="fu">list</span>( <span class="at">v1 =</span>V<span class="fl">.1</span><span class="sc">~</span> bpreis <span class="sc">*</span> alt1.x1 ,</span>
+<span id="cb2-54"><a href="#cb2-54" tabindex="-1"></a> <span class="at">v2 =</span>V<span class="fl">.2</span><span class="sc">~</span> bpreis <span class="sc">*</span> alt2.x1)</span>
+<span id="cb2-55"><a href="#cb2-55" tabindex="-1"></a></span>
+<span id="cb2-56"><a href="#cb2-56" tabindex="-1"></a>)</span>
+<span id="cb2-57"><a href="#cb2-57" tabindex="-1"></a></span>
+<span id="cb2-58"><a href="#cb2-58" tabindex="-1"></a></span>
+<span id="cb2-59"><a href="#cb2-59" tabindex="-1"></a>destype<span class="ot">=</span><span class="st">"ngene"</span></span>
+<span id="cb2-60"><a href="#cb2-60" tabindex="-1"></a></span>
+<span id="cb2-61"><a href="#cb2-61" tabindex="-1"></a>sedrive <span class="ot"><-</span> <span class="fu">sim_all</span>(<span class="at">nosim =</span> nosim, <span class="at">resps=</span>resps, <span class="at">destype =</span> destype,</span>
+<span id="cb2-62"><a href="#cb2-62" tabindex="-1"></a> <span class="at">designpath =</span> designpath, <span class="at">u=</span>ul, <span class="at">bcoeff =</span> bcoeff)</span>
+<span id="cb2-63"><a href="#cb2-63" tabindex="-1"></a><span class="co">#> Utility function used in simulation, ie the true utility: </span></span>
+<span id="cb2-64"><a href="#cb2-64" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-65"><a href="#cb2-65" tabindex="-1"></a><span class="co">#> $u1</span></span>
+<span id="cb2-66"><a href="#cb2-66" tabindex="-1"></a><span class="co">#> $u1$v1</span></span>
+<span id="cb2-67"><a href="#cb2-67" tabindex="-1"></a><span class="co">#> V.1 ~ bpreis * alt1.x1 + blade * alt1.x2 + bwarte * alt1.x3</span></span>
+<span id="cb2-68"><a href="#cb2-68" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-69"><a href="#cb2-69" tabindex="-1"></a><span class="co">#> $u1$v2</span></span>
+<span id="cb2-70"><a href="#cb2-70" tabindex="-1"></a><span class="co">#> V.2 ~ bpreis * alt2.x1 + blade * alt2.x2 + bwarte * alt2.x3</span></span>
+<span id="cb2-71"><a href="#cb2-71" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-72"><a href="#cb2-72" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-73"><a href="#cb2-73" tabindex="-1"></a><span class="co">#> $u2</span></span>
+<span id="cb2-74"><a href="#cb2-74" tabindex="-1"></a><span class="co">#> $u2$v1</span></span>
+<span id="cb2-75"><a href="#cb2-75" tabindex="-1"></a><span class="co">#> V.1 ~ bpreis * alt1.x1</span></span>
+<span id="cb2-76"><a href="#cb2-76" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-77"><a href="#cb2-77" tabindex="-1"></a><span class="co">#> $u2$v2</span></span>
+<span id="cb2-78"><a href="#cb2-78" tabindex="-1"></a><span class="co">#> V.2 ~ bpreis * alt2.x1</span></span>
+<span id="cb2-79"><a href="#cb2-79" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-80"><a href="#cb2-80" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-81"><a href="#cb2-81" tabindex="-1"></a><span class="co">#> Utility function used for Logit estimation with mixl: </span></span>
+<span id="cb2-82"><a href="#cb2-82" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-83"><a href="#cb2-83" tabindex="-1"></a><span class="co">#> [1] "U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;"</span></span>
+<span id="cb2-84"><a href="#cb2-84" tabindex="-1"></a><span class="co">#> New names:</span></span>
+<span id="cb2-85"><a href="#cb2-85" tabindex="-1"></a><span class="co">#> • `Choice situation` -> `Choice.situation`</span></span>
+<span id="cb2-86"><a href="#cb2-86" tabindex="-1"></a><span class="co">#> • `` -> `...10`</span></span>
+<span id="cb2-87"><a href="#cb2-87" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-88"><a href="#cb2-88" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-89"><a href="#cb2-89" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-90"><a href="#cb2-90" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-91"><a href="#cb2-91" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-92"><a href="#cb2-92" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-93"><a href="#cb2-93" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-94"><a href="#cb2-94" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-95"><a href="#cb2-95" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-96"><a href="#cb2-96" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-97"><a href="#cb2-97" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-98"><a href="#cb2-98" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-99"><a href="#cb2-99" tabindex="-1"></a><span class="co">#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2</span></span>
+<span id="cb2-100"><a href="#cb2-100" tabindex="-1"></a><span class="co">#> 1 1 7 80 2.5 10.0 60 20.0 10 1 1 -0.775 -1.800 -0.15343271 3.6612318 -0.9284327 1.8612318</span></span>
+<span id="cb2-101"><a href="#cb2-101" tabindex="-1"></a><span class="co">#> 2 1 19 20 2.5 5.0 60 2.5 0 1 1 -0.275 -0.775 0.47936686 -0.8086989 0.2043669 -1.5836989</span></span>
+<span id="cb2-102"><a href="#cb2-102" tabindex="-1"></a><span class="co">#> 3 1 30 20 10.0 5.0 80 5.0 10 1 1 -0.800 -0.950 0.12634298 1.2300690 -0.6736570 0.2800690</span></span>
+<span id="cb2-103"><a href="#cb2-103" tabindex="-1"></a><span class="co">#> 4 1 32 40 20.0 2.5 80 2.5 0 1 1 -1.750 -0.975 2.08710825 -0.1882935 0.3371082 -1.1632935</span></span>
+<span id="cb2-104"><a href="#cb2-104" tabindex="-1"></a><span class="co">#> 5 1 39 40 20.0 0.0 80 10.0 10 1 1 -1.800 -1.300 1.05540385 3.1339326 -0.7445961 1.8339326</span></span>
+<span id="cb2-105"><a href="#cb2-105" tabindex="-1"></a><span class="co">#> 6 1 48 60 5.0 2.5 20 5.0 10 1 1 -0.900 -0.350 0.07255885 -0.1156742 -0.8274412 -0.4656742</span></span>
+<span id="cb2-106"><a href="#cb2-106" tabindex="-1"></a><span class="co">#> CHOICE</span></span>
+<span id="cb2-107"><a href="#cb2-107" tabindex="-1"></a><span class="co">#> 1 2</span></span>
+<span id="cb2-108"><a href="#cb2-108" tabindex="-1"></a><span class="co">#> 2 1</span></span>
+<span id="cb2-109"><a href="#cb2-109" tabindex="-1"></a><span class="co">#> 3 2</span></span>
+<span id="cb2-110"><a href="#cb2-110" tabindex="-1"></a><span class="co">#> 4 1</span></span>
+<span id="cb2-111"><a href="#cb2-111" tabindex="-1"></a><span class="co">#> 5 2</span></span>
+<span id="cb2-112"><a href="#cb2-112" tabindex="-1"></a><span class="co">#> 6 2</span></span>
+<span id="cb2-113"><a href="#cb2-113" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-114"><a href="#cb2-114" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-115"><a href="#cb2-115" tabindex="-1"></a><span class="co">#> This is Run number 1 </span></span>
+<span id="cb2-116"><a href="#cb2-116" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-117"><a href="#cb2-117" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-118"><a href="#cb2-118" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-119"><a href="#cb2-119" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-120"><a href="#cb2-120" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-121"><a href="#cb2-121" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-122"><a href="#cb2-122" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-123"><a href="#cb2-123" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-124"><a href="#cb2-124" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-125"><a href="#cb2-125" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-126"><a href="#cb2-126" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-127"><a href="#cb2-127" tabindex="-1"></a><span class="co">#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2</span></span>
+<span id="cb2-128"><a href="#cb2-128" tabindex="-1"></a><span class="co">#> 1 1 7 80 2.5 10.0 60 20.0 10 1 1 -0.775 -1.800 -1.2775839 1.5689946 -2.052584 -0.2310054</span></span>
+<span id="cb2-129"><a href="#cb2-129" tabindex="-1"></a><span class="co">#> 2 1 19 20 2.5 5.0 60 2.5 0 1 1 -0.275 -0.775 0.5934850 0.5453996 0.318485 -0.2296004</span></span>
+<span id="cb2-130"><a href="#cb2-130" tabindex="-1"></a><span class="co">#> 3 1 30 20 10.0 5.0 80 5.0 10 1 1 -0.800 -0.950 -0.5127855 1.7551185 -1.312785 0.8051185</span></span>
+<span id="cb2-131"><a href="#cb2-131" tabindex="-1"></a><span class="co">#> 4 1 32 40 20.0 2.5 80 2.5 0 1 1 -1.750 -0.975 3.4643234 1.3685812 1.714323 0.3935812</span></span>
+<span id="cb2-132"><a href="#cb2-132" tabindex="-1"></a><span class="co">#> 5 1 39 40 20.0 0.0 80 10.0 10 1 1 -1.800 -1.300 -0.5128262 0.3011019 -2.312826 -0.9988981</span></span>
+<span id="cb2-133"><a href="#cb2-133" tabindex="-1"></a><span class="co">#> 6 1 48 60 5.0 2.5 20 5.0 10 1 1 -0.900 -0.350 4.3343477 1.2265189 3.434348 0.8765189</span></span>
+<span id="cb2-134"><a href="#cb2-134" tabindex="-1"></a><span class="co">#> CHOICE</span></span>
+<span id="cb2-135"><a href="#cb2-135" tabindex="-1"></a><span class="co">#> 1 2</span></span>
+<span id="cb2-136"><a href="#cb2-136" tabindex="-1"></a><span class="co">#> 2 1</span></span>
+<span id="cb2-137"><a href="#cb2-137" tabindex="-1"></a><span class="co">#> 3 2</span></span>
+<span id="cb2-138"><a href="#cb2-138" tabindex="-1"></a><span class="co">#> 4 1</span></span>
+<span id="cb2-139"><a href="#cb2-139" tabindex="-1"></a><span class="co">#> 5 2</span></span>
+<span id="cb2-140"><a href="#cb2-140" tabindex="-1"></a><span class="co">#> 6 1</span></span>
+<span id="cb2-141"><a href="#cb2-141" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-142"><a href="#cb2-142" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-143"><a href="#cb2-143" tabindex="-1"></a><span class="co">#> This is the utility functions </span></span>
+<span id="cb2-144"><a href="#cb2-144" tabindex="-1"></a><span class="co">#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319 </span></span>
+<span id="cb2-145"><a href="#cb2-145" tabindex="-1"></a><span class="co">#> Initial gradient value:</span></span>
+<span id="cb2-146"><a href="#cb2-146" tabindex="-1"></a><span class="co">#> bpreis blade bwarte </span></span>
+<span id="cb2-147"><a href="#cb2-147" tabindex="-1"></a><span class="co">#> -1060.0 -812.5 520.0 </span></span>
+<span id="cb2-148"><a href="#cb2-148" tabindex="-1"></a><span class="co">#> initial value 998.131940 </span></span>
+<span id="cb2-149"><a href="#cb2-149" tabindex="-1"></a><span class="co">#> iter 2 value 994.260781</span></span>
+<span id="cb2-150"><a href="#cb2-150" tabindex="-1"></a><span class="co">#> iter 3 value 974.092906</span></span>
+<span id="cb2-151"><a href="#cb2-151" tabindex="-1"></a><span class="co">#> iter 4 value 973.856287</span></span>
+<span id="cb2-152"><a href="#cb2-152" tabindex="-1"></a><span class="co">#> iter 5 value 970.270450</span></span>
+<span id="cb2-153"><a href="#cb2-153" tabindex="-1"></a><span class="co">#> iter 6 value 970.262794</span></span>
+<span id="cb2-154"><a href="#cb2-154" tabindex="-1"></a><span class="co">#> iter 6 value 970.262788</span></span>
+<span id="cb2-155"><a href="#cb2-155" tabindex="-1"></a><span class="co">#> iter 6 value 970.262788</span></span>
+<span id="cb2-156"><a href="#cb2-156" tabindex="-1"></a><span class="co">#> final value 970.262788 </span></span>
+<span id="cb2-157"><a href="#cb2-157" tabindex="-1"></a><span class="co">#> converged</span></span>
+<span id="cb2-158"><a href="#cb2-158" tabindex="-1"></a><span class="co">#> This is Run number 2 </span></span>
+<span id="cb2-159"><a href="#cb2-159" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-160"><a href="#cb2-160" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-161"><a href="#cb2-161" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-162"><a href="#cb2-162" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-163"><a href="#cb2-163" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-164"><a href="#cb2-164" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-165"><a href="#cb2-165" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-166"><a href="#cb2-166" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-167"><a href="#cb2-167" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-168"><a href="#cb2-168" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-169"><a href="#cb2-169" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-170"><a href="#cb2-170" tabindex="-1"></a><span class="co">#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2</span></span>
+<span id="cb2-171"><a href="#cb2-171" tabindex="-1"></a><span class="co">#> 1 1 7 80 2.5 10.0 60 20.0 10 1 1 -0.775 -1.800 0.34553136 -0.8375727 -0.4294686 -2.6375727</span></span>
+<span id="cb2-172"><a href="#cb2-172" tabindex="-1"></a><span class="co">#> 2 1 19 20 2.5 5.0 60 2.5 0 1 1 -0.275 -0.775 -1.32361481 0.3195766 -1.5986148 -0.4554234</span></span>
+<span id="cb2-173"><a href="#cb2-173" tabindex="-1"></a><span class="co">#> 3 1 30 20 10.0 5.0 80 5.0 10 1 1 -0.800 -0.950 0.08515524 -0.6090259 -0.7148448 -1.5590259</span></span>
+<span id="cb2-174"><a href="#cb2-174" tabindex="-1"></a><span class="co">#> 4 1 32 40 20.0 2.5 80 2.5 0 1 1 -1.750 -0.975 -0.18021132 2.3073397 -1.9302113 1.3323397</span></span>
+<span id="cb2-175"><a href="#cb2-175" tabindex="-1"></a><span class="co">#> 5 1 39 40 20.0 0.0 80 10.0 10 1 1 -1.800 -1.300 -0.55591900 3.4630292 -2.3559190 2.1630292</span></span>
+<span id="cb2-176"><a href="#cb2-176" tabindex="-1"></a><span class="co">#> 6 1 48 60 5.0 2.5 20 5.0 10 1 1 -0.900 -0.350 -0.29734711 3.0420404 -1.1973471 2.6920404</span></span>
+<span id="cb2-177"><a href="#cb2-177" tabindex="-1"></a><span class="co">#> CHOICE</span></span>
+<span id="cb2-178"><a href="#cb2-178" tabindex="-1"></a><span class="co">#> 1 1</span></span>
+<span id="cb2-179"><a href="#cb2-179" tabindex="-1"></a><span class="co">#> 2 2</span></span>
+<span id="cb2-180"><a href="#cb2-180" tabindex="-1"></a><span class="co">#> 3 1</span></span>
+<span id="cb2-181"><a href="#cb2-181" tabindex="-1"></a><span class="co">#> 4 2</span></span>
+<span id="cb2-182"><a href="#cb2-182" tabindex="-1"></a><span class="co">#> 5 2</span></span>
+<span id="cb2-183"><a href="#cb2-183" tabindex="-1"></a><span class="co">#> 6 2</span></span>
+<span id="cb2-184"><a href="#cb2-184" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-185"><a href="#cb2-185" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-186"><a href="#cb2-186" tabindex="-1"></a><span class="co">#> This is the utility functions </span></span>
+<span id="cb2-187"><a href="#cb2-187" tabindex="-1"></a><span class="co">#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319 </span></span>
+<span id="cb2-188"><a href="#cb2-188" tabindex="-1"></a><span class="co">#> Initial gradient value:</span></span>
+<span id="cb2-189"><a href="#cb2-189" tabindex="-1"></a><span class="co">#> bpreis blade bwarte </span></span>
+<span id="cb2-190"><a href="#cb2-190" tabindex="-1"></a><span class="co">#> 440.0 -1087.5 447.5 </span></span>
+<span id="cb2-191"><a href="#cb2-191" tabindex="-1"></a><span class="co">#> initial value 998.131940 </span></span>
+<span id="cb2-192"><a href="#cb2-192" tabindex="-1"></a><span class="co">#> iter 2 value 995.094499</span></span>
+<span id="cb2-193"><a href="#cb2-193" tabindex="-1"></a><span class="co">#> iter 3 value 974.488144</span></span>
+<span id="cb2-194"><a href="#cb2-194" tabindex="-1"></a><span class="co">#> iter 4 value 974.227531</span></span>
+<span id="cb2-195"><a href="#cb2-195" tabindex="-1"></a><span class="co">#> iter 5 value 971.482008</span></span>
+<span id="cb2-196"><a href="#cb2-196" tabindex="-1"></a><span class="co">#> iter 6 value 971.477251</span></span>
+<span id="cb2-197"><a href="#cb2-197" tabindex="-1"></a><span class="co">#> iter 6 value 971.477249</span></span>
+<span id="cb2-198"><a href="#cb2-198" tabindex="-1"></a><span class="co">#> iter 6 value 971.477249</span></span>
+<span id="cb2-199"><a href="#cb2-199" tabindex="-1"></a><span class="co">#> final value 971.477249 </span></span>
+<span id="cb2-200"><a href="#cb2-200" tabindex="-1"></a><span class="co">#> converged</span></span>
+<span id="cb2-201"><a href="#cb2-201" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-202"><a href="#cb2-202" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-203"><a href="#cb2-203" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-204"><a href="#cb2-204" tabindex="-1"></a><span class="co">#> \ vars n mean sd min max range se</span></span>
+<span id="cb2-205"><a href="#cb2-205" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-206"><a href="#cb2-206" tabindex="-1"></a><span class="co">#> est_bpreis 1 2 -0.01 0.00 -0.01 0.00 0.00 0.00</span></span>
+<span id="cb2-207"><a href="#cb2-207" tabindex="-1"></a><span class="co">#> est_blade 2 2 -0.04 0.00 -0.04 -0.04 0.00 0.00</span></span>
+<span id="cb2-208"><a href="#cb2-208" tabindex="-1"></a><span class="co">#> est_bwarte 3 2 0.03 0.00 0.03 0.03 0.00 0.00</span></span>
+<span id="cb2-209"><a href="#cb2-209" tabindex="-1"></a><span class="co">#> rob_pval0_bpreis 4 2 0.01 0.01 0.00 0.02 0.02 0.01</span></span>
+<span id="cb2-210"><a href="#cb2-210" tabindex="-1"></a><span class="co">#> rob_pval0_blade 5 2 0.00 0.00 0.00 0.00 0.00 0.00</span></span>
+<span id="cb2-211"><a href="#cb2-211" tabindex="-1"></a><span class="co">#> rob_pval0_bwarte 6 2 0.01 0.00 0.01 0.01 0.00 0.00</span></span>
+<span id="cb2-212"><a href="#cb2-212" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-213"><a href="#cb2-213" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-214"><a href="#cb2-214" tabindex="-1"></a><span class="co">#> TRUE </span></span>
+<span id="cb2-215"><a href="#cb2-215" tabindex="-1"></a><span class="co">#> 100 </span></span>
+<span id="cb2-216"><a href="#cb2-216" tabindex="-1"></a><span class="co">#> Utility function used in simulation, ie the true utility: </span></span>
+<span id="cb2-217"><a href="#cb2-217" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-218"><a href="#cb2-218" tabindex="-1"></a><span class="co">#> $u1</span></span>
+<span id="cb2-219"><a href="#cb2-219" tabindex="-1"></a><span class="co">#> $u1$v1</span></span>
+<span id="cb2-220"><a href="#cb2-220" tabindex="-1"></a><span class="co">#> V.1 ~ bpreis * alt1.x1 + blade * alt1.x2 + bwarte * alt1.x3</span></span>
+<span id="cb2-221"><a href="#cb2-221" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-222"><a href="#cb2-222" tabindex="-1"></a><span class="co">#> $u1$v2</span></span>
+<span id="cb2-223"><a href="#cb2-223" tabindex="-1"></a><span class="co">#> V.2 ~ bpreis * alt2.x1 + blade * alt2.x2 + bwarte * alt2.x3</span></span>
+<span id="cb2-224"><a href="#cb2-224" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-225"><a href="#cb2-225" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-226"><a href="#cb2-226" tabindex="-1"></a><span class="co">#> $u2</span></span>
+<span id="cb2-227"><a href="#cb2-227" tabindex="-1"></a><span class="co">#> $u2$v1</span></span>
+<span id="cb2-228"><a href="#cb2-228" tabindex="-1"></a><span class="co">#> V.1 ~ bpreis * alt1.x1</span></span>
+<span id="cb2-229"><a href="#cb2-229" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-230"><a href="#cb2-230" tabindex="-1"></a><span class="co">#> $u2$v2</span></span>
+<span id="cb2-231"><a href="#cb2-231" tabindex="-1"></a><span class="co">#> V.2 ~ bpreis * alt2.x1</span></span>
+<span id="cb2-232"><a href="#cb2-232" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-233"><a href="#cb2-233" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-234"><a href="#cb2-234" tabindex="-1"></a><span class="co">#> Utility function used for Logit estimation with mixl: </span></span>
+<span id="cb2-235"><a href="#cb2-235" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-236"><a href="#cb2-236" tabindex="-1"></a><span class="co">#> [1] "U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;"</span></span>
+<span id="cb2-237"><a href="#cb2-237" tabindex="-1"></a><span class="co">#> New names:</span></span>
+<span id="cb2-238"><a href="#cb2-238" tabindex="-1"></a><span class="co">#> • `Choice situation` -> `Choice.situation`</span></span>
+<span id="cb2-239"><a href="#cb2-239" tabindex="-1"></a><span class="co">#> • `` -> `...10`</span></span>
+<span id="cb2-240"><a href="#cb2-240" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-241"><a href="#cb2-241" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-242"><a href="#cb2-242" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-243"><a href="#cb2-243" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-244"><a href="#cb2-244" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-245"><a href="#cb2-245" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-246"><a href="#cb2-246" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-247"><a href="#cb2-247" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-248"><a href="#cb2-248" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-249"><a href="#cb2-249" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-250"><a href="#cb2-250" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-251"><a href="#cb2-251" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-252"><a href="#cb2-252" tabindex="-1"></a><span class="co">#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2</span></span>
+<span id="cb2-253"><a href="#cb2-253" tabindex="-1"></a><span class="co">#> 1 1 12 60 2.5 0.0 20 20.0 10 1 1 -0.775 -1.400 0.63130736 -1.4347994 -0.1436926 -2.8347994</span></span>
+<span id="cb2-254"><a href="#cb2-254" tabindex="-1"></a><span class="co">#> 2 1 16 20 10.0 5.0 40 5.0 0 1 1 -0.800 -0.750 5.09739937 0.4118885 4.2973994 -0.3381115</span></span>
+<span id="cb2-255"><a href="#cb2-255" tabindex="-1"></a><span class="co">#> 3 1 17 20 20.0 0.0 80 10.0 10 1 1 -1.600 -1.300 0.22397799 0.4666321 -1.3760220 -0.8333679</span></span>
+<span id="cb2-256"><a href="#cb2-256" tabindex="-1"></a><span class="co">#> 4 1 25 60 5.0 10.0 20 20.0 5 1 1 -0.750 -1.500 -0.05146482 2.2007592 -0.8014648 0.7007592</span></span>
+<span id="cb2-257"><a href="#cb2-257" tabindex="-1"></a><span class="co">#> 5 1 29 20 5.0 10.0 80 5.0 0 1 1 -0.350 -1.150 1.57620781 4.9154679 1.2262078 3.7654679</span></span>
+<span id="cb2-258"><a href="#cb2-258" tabindex="-1"></a><span class="co">#> 6 1 32 40 10.0 2.5 80 2.5 5 1 1 -1.050 -0.875 -0.47930823 0.7058788 -1.5293082 -0.1691212</span></span>
+<span id="cb2-259"><a href="#cb2-259" tabindex="-1"></a><span class="co">#> CHOICE</span></span>
+<span id="cb2-260"><a href="#cb2-260" tabindex="-1"></a><span class="co">#> 1 1</span></span>
+<span id="cb2-261"><a href="#cb2-261" tabindex="-1"></a><span class="co">#> 2 1</span></span>
+<span id="cb2-262"><a href="#cb2-262" tabindex="-1"></a><span class="co">#> 3 2</span></span>
+<span id="cb2-263"><a href="#cb2-263" tabindex="-1"></a><span class="co">#> 4 2</span></span>
+<span id="cb2-264"><a href="#cb2-264" tabindex="-1"></a><span class="co">#> 5 2</span></span>
+<span id="cb2-265"><a href="#cb2-265" tabindex="-1"></a><span class="co">#> 6 2</span></span>
+<span id="cb2-266"><a href="#cb2-266" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-267"><a href="#cb2-267" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-268"><a href="#cb2-268" tabindex="-1"></a><span class="co">#> This is Run number 1 </span></span>
+<span id="cb2-269"><a href="#cb2-269" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-270"><a href="#cb2-270" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-271"><a href="#cb2-271" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-272"><a href="#cb2-272" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-273"><a href="#cb2-273" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-274"><a href="#cb2-274" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-275"><a href="#cb2-275" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-276"><a href="#cb2-276" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-277"><a href="#cb2-277" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-278"><a href="#cb2-278" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-279"><a href="#cb2-279" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-280"><a href="#cb2-280" tabindex="-1"></a><span class="co">#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2</span></span>
+<span id="cb2-281"><a href="#cb2-281" tabindex="-1"></a><span class="co">#> 1 1 12 60 2.5 0.0 20 20.0 10 1 1 -0.775 -1.400 0.3494617 0.1551114 -0.42553827 -1.24488857</span></span>
+<span id="cb2-282"><a href="#cb2-282" tabindex="-1"></a><span class="co">#> 2 1 16 20 10.0 5.0 40 5.0 0 1 1 -0.800 -0.750 1.5845207 0.5556039 0.78452066 -0.19439613</span></span>
+<span id="cb2-283"><a href="#cb2-283" tabindex="-1"></a><span class="co">#> 3 1 17 20 20.0 0.0 80 10.0 10 1 1 -1.600 -1.300 4.1993459 -0.1612424 2.59934589 -1.46124241</span></span>
+<span id="cb2-284"><a href="#cb2-284" tabindex="-1"></a><span class="co">#> 4 1 25 60 5.0 10.0 20 20.0 5 1 1 -0.750 -1.500 0.6527215 1.3949219 -0.09727852 -0.10507806</span></span>
+<span id="cb2-285"><a href="#cb2-285" tabindex="-1"></a><span class="co">#> 5 1 29 20 5.0 10.0 80 5.0 0 1 1 -0.350 -1.150 2.6927356 -1.3232777 2.34273564 -2.47327770</span></span>
+<span id="cb2-286"><a href="#cb2-286" tabindex="-1"></a><span class="co">#> 6 1 32 40 10.0 2.5 80 2.5 5 1 1 -1.050 -0.875 0.3758168 0.8556930 -0.67418318 -0.01930696</span></span>
+<span id="cb2-287"><a href="#cb2-287" tabindex="-1"></a><span class="co">#> CHOICE</span></span>
+<span id="cb2-288"><a href="#cb2-288" tabindex="-1"></a><span class="co">#> 1 1</span></span>
+<span id="cb2-289"><a href="#cb2-289" tabindex="-1"></a><span class="co">#> 2 1</span></span>
+<span id="cb2-290"><a href="#cb2-290" tabindex="-1"></a><span class="co">#> 3 1</span></span>
+<span id="cb2-291"><a href="#cb2-291" tabindex="-1"></a><span class="co">#> 4 1</span></span>
+<span id="cb2-292"><a href="#cb2-292" tabindex="-1"></a><span class="co">#> 5 1</span></span>
+<span id="cb2-293"><a href="#cb2-293" tabindex="-1"></a><span class="co">#> 6 2</span></span>
+<span id="cb2-294"><a href="#cb2-294" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-295"><a href="#cb2-295" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-296"><a href="#cb2-296" tabindex="-1"></a><span class="co">#> This is the utility functions </span></span>
+<span id="cb2-297"><a href="#cb2-297" tabindex="-1"></a><span class="co">#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319 </span></span>
+<span id="cb2-298"><a href="#cb2-298" tabindex="-1"></a><span class="co">#> Initial gradient value:</span></span>
+<span id="cb2-299"><a href="#cb2-299" tabindex="-1"></a><span class="co">#> bpreis blade bwarte </span></span>
+<span id="cb2-300"><a href="#cb2-300" tabindex="-1"></a><span class="co">#> -2340.0 -857.5 510.0 </span></span>
+<span id="cb2-301"><a href="#cb2-301" tabindex="-1"></a><span class="co">#> initial value 998.131940 </span></span>
+<span id="cb2-302"><a href="#cb2-302" tabindex="-1"></a><span class="co">#> iter 2 value 989.566757</span></span>
+<span id="cb2-303"><a href="#cb2-303" tabindex="-1"></a><span class="co">#> iter 3 value 968.906950</span></span>
+<span id="cb2-304"><a href="#cb2-304" tabindex="-1"></a><span class="co">#> iter 4 value 968.775516</span></span>
+<span id="cb2-305"><a href="#cb2-305" tabindex="-1"></a><span class="co">#> iter 5 value 959.377427</span></span>
+<span id="cb2-306"><a href="#cb2-306" tabindex="-1"></a><span class="co">#> iter 6 value 959.364632</span></span>
+<span id="cb2-307"><a href="#cb2-307" tabindex="-1"></a><span class="co">#> iter 7 value 959.364588</span></span>
+<span id="cb2-308"><a href="#cb2-308" tabindex="-1"></a><span class="co">#> iter 7 value 959.364588</span></span>
+<span id="cb2-309"><a href="#cb2-309" tabindex="-1"></a><span class="co">#> iter 7 value 959.364588</span></span>
+<span id="cb2-310"><a href="#cb2-310" tabindex="-1"></a><span class="co">#> final value 959.364588 </span></span>
+<span id="cb2-311"><a href="#cb2-311" tabindex="-1"></a><span class="co">#> converged</span></span>
+<span id="cb2-312"><a href="#cb2-312" tabindex="-1"></a><span class="co">#> This is Run number 2 </span></span>
+<span id="cb2-313"><a href="#cb2-313" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-314"><a href="#cb2-314" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-315"><a href="#cb2-315" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-316"><a href="#cb2-316" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-317"><a href="#cb2-317" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-318"><a href="#cb2-318" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-319"><a href="#cb2-319" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-320"><a href="#cb2-320" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-321"><a href="#cb2-321" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-322"><a href="#cb2-322" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-323"><a href="#cb2-323" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-324"><a href="#cb2-324" tabindex="-1"></a><span class="co">#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1</span></span>
+<span id="cb2-325"><a href="#cb2-325" tabindex="-1"></a><span class="co">#> 1 1 12 60 2.5 0.0 20 20.0 10 1 1 -0.775 -1.400 -0.5067469 -4.908678e-05 -1.2817469</span></span>
+<span id="cb2-326"><a href="#cb2-326" tabindex="-1"></a><span class="co">#> 2 1 16 20 10.0 5.0 40 5.0 0 1 1 -0.800 -0.750 2.1209149 5.835693e-01 1.3209149</span></span>
+<span id="cb2-327"><a href="#cb2-327" tabindex="-1"></a><span class="co">#> 3 1 17 20 20.0 0.0 80 10.0 10 1 1 -1.600 -1.300 -0.3310010 7.106139e-01 -1.9310010</span></span>
+<span id="cb2-328"><a href="#cb2-328" tabindex="-1"></a><span class="co">#> 4 1 25 60 5.0 10.0 20 20.0 5 1 1 -0.750 -1.500 1.0469501 3.053872e-01 0.2969501</span></span>
+<span id="cb2-329"><a href="#cb2-329" tabindex="-1"></a><span class="co">#> 5 1 29 20 5.0 10.0 80 5.0 0 1 1 -0.350 -1.150 1.2182730 -6.215119e-01 0.8682730</span></span>
+<span id="cb2-330"><a href="#cb2-330" tabindex="-1"></a><span class="co">#> 6 1 32 40 10.0 2.5 80 2.5 5 1 1 -1.050 -0.875 -0.3318808 5.251218e+00 -1.3818808</span></span>
+<span id="cb2-331"><a href="#cb2-331" tabindex="-1"></a><span class="co">#> U_2 CHOICE</span></span>
+<span id="cb2-332"><a href="#cb2-332" tabindex="-1"></a><span class="co">#> 1 -1.4000491 1</span></span>
+<span id="cb2-333"><a href="#cb2-333" tabindex="-1"></a><span class="co">#> 2 -0.1664307 1</span></span>
+<span id="cb2-334"><a href="#cb2-334" tabindex="-1"></a><span class="co">#> 3 -0.5893861 2</span></span>
+<span id="cb2-335"><a href="#cb2-335" tabindex="-1"></a><span class="co">#> 4 -1.1946128 1</span></span>
+<span id="cb2-336"><a href="#cb2-336" tabindex="-1"></a><span class="co">#> 5 -1.7715119 1</span></span>
+<span id="cb2-337"><a href="#cb2-337" tabindex="-1"></a><span class="co">#> 6 4.3762180 2</span></span>
+<span id="cb2-338"><a href="#cb2-338" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-339"><a href="#cb2-339" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-340"><a href="#cb2-340" tabindex="-1"></a><span class="co">#> This is the utility functions </span></span>
+<span id="cb2-341"><a href="#cb2-341" tabindex="-1"></a><span class="co">#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319 </span></span>
+<span id="cb2-342"><a href="#cb2-342" tabindex="-1"></a><span class="co">#> Initial gradient value:</span></span>
+<span id="cb2-343"><a href="#cb2-343" tabindex="-1"></a><span class="co">#> bpreis blade bwarte </span></span>
+<span id="cb2-344"><a href="#cb2-344" tabindex="-1"></a><span class="co">#> -2120.0 -842.5 582.5 </span></span>
+<span id="cb2-345"><a href="#cb2-345" tabindex="-1"></a><span class="co">#> initial value 998.131940 </span></span>
+<span id="cb2-346"><a href="#cb2-346" tabindex="-1"></a><span class="co">#> iter 2 value 990.498814</span></span>
+<span id="cb2-347"><a href="#cb2-347" tabindex="-1"></a><span class="co">#> iter 3 value 970.036278</span></span>
+<span id="cb2-348"><a href="#cb2-348" tabindex="-1"></a><span class="co">#> iter 4 value 970.031934</span></span>
+<span id="cb2-349"><a href="#cb2-349" tabindex="-1"></a><span class="co">#> iter 5 value 961.943463</span></span>
+<span id="cb2-350"><a href="#cb2-350" tabindex="-1"></a><span class="co">#> iter 6 value 961.698866</span></span>
+<span id="cb2-351"><a href="#cb2-351" tabindex="-1"></a><span class="co">#> iter 7 value 961.698562</span></span>
+<span id="cb2-352"><a href="#cb2-352" tabindex="-1"></a><span class="co">#> iter 7 value 961.698561</span></span>
+<span id="cb2-353"><a href="#cb2-353" tabindex="-1"></a><span class="co">#> iter 7 value 961.698561</span></span>
+<span id="cb2-354"><a href="#cb2-354" tabindex="-1"></a><span class="co">#> final value 961.698561 </span></span>
+<span id="cb2-355"><a href="#cb2-355" tabindex="-1"></a><span class="co">#> converged</span></span>
+<span id="cb2-356"><a href="#cb2-356" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-357"><a href="#cb2-357" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-358"><a href="#cb2-358" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-359"><a href="#cb2-359" tabindex="-1"></a><span class="co">#> \ vars n mean sd min max range se</span></span>
+<span id="cb2-360"><a href="#cb2-360" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-361"><a href="#cb2-361" tabindex="-1"></a><span class="co">#> est_bpreis 1 2 -0.01 0.00 -0.01 -0.01 0.00 0.00</span></span>
+<span id="cb2-362"><a href="#cb2-362" tabindex="-1"></a><span class="co">#> est_blade 2 2 -0.05 0.00 -0.05 -0.05 0.00 0.00</span></span>
+<span id="cb2-363"><a href="#cb2-363" tabindex="-1"></a><span class="co">#> est_bwarte 3 2 0.02 0.01 0.01 0.02 0.01 0.00</span></span>
+<span id="cb2-364"><a href="#cb2-364" tabindex="-1"></a><span class="co">#> rob_pval0_bpreis 4 2 0.00 0.00 0.00 0.00 0.00 0.00</span></span>
+<span id="cb2-365"><a href="#cb2-365" tabindex="-1"></a><span class="co">#> rob_pval0_blade 5 2 0.00 0.00 0.00 0.00 0.00 0.00</span></span>
+<span id="cb2-366"><a href="#cb2-366" tabindex="-1"></a><span class="co">#> rob_pval0_bwarte 6 2 0.16 0.19 0.03 0.30 0.27 0.13</span></span>
+<span id="cb2-367"><a href="#cb2-367" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-368"><a href="#cb2-368" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-369"><a href="#cb2-369" tabindex="-1"></a><span class="co">#> FALSE TRUE </span></span>
+<span id="cb2-370"><a href="#cb2-370" tabindex="-1"></a><span class="co">#> 50 50 </span></span>
+<span id="cb2-371"><a href="#cb2-371" tabindex="-1"></a><span class="co">#> Utility function used in simulation, ie the true utility: </span></span>
+<span id="cb2-372"><a href="#cb2-372" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-373"><a href="#cb2-373" tabindex="-1"></a><span class="co">#> $u1</span></span>
+<span id="cb2-374"><a href="#cb2-374" tabindex="-1"></a><span class="co">#> $u1$v1</span></span>
+<span id="cb2-375"><a href="#cb2-375" tabindex="-1"></a><span class="co">#> V.1 ~ bpreis * alt1.x1 + blade * alt1.x2 + bwarte * alt1.x3</span></span>
+<span id="cb2-376"><a href="#cb2-376" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-377"><a href="#cb2-377" tabindex="-1"></a><span class="co">#> $u1$v2</span></span>
+<span id="cb2-378"><a href="#cb2-378" tabindex="-1"></a><span class="co">#> V.2 ~ bpreis * alt2.x1 + blade * alt2.x2 + bwarte * alt2.x3</span></span>
+<span id="cb2-379"><a href="#cb2-379" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-380"><a href="#cb2-380" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-381"><a href="#cb2-381" tabindex="-1"></a><span class="co">#> $u2</span></span>
+<span id="cb2-382"><a href="#cb2-382" tabindex="-1"></a><span class="co">#> $u2$v1</span></span>
+<span id="cb2-383"><a href="#cb2-383" tabindex="-1"></a><span class="co">#> V.1 ~ bpreis * alt1.x1</span></span>
+<span id="cb2-384"><a href="#cb2-384" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-385"><a href="#cb2-385" tabindex="-1"></a><span class="co">#> $u2$v2</span></span>
+<span id="cb2-386"><a href="#cb2-386" tabindex="-1"></a><span class="co">#> V.2 ~ bpreis * alt2.x1</span></span>
+<span id="cb2-387"><a href="#cb2-387" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-388"><a href="#cb2-388" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-389"><a href="#cb2-389" tabindex="-1"></a><span class="co">#> Utility function used for Logit estimation with mixl: </span></span>
+<span id="cb2-390"><a href="#cb2-390" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-391"><a href="#cb2-391" tabindex="-1"></a><span class="co">#> [1] "U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;"</span></span>
+<span id="cb2-392"><a href="#cb2-392" tabindex="-1"></a><span class="co">#> New names:</span></span>
+<span id="cb2-393"><a href="#cb2-393" tabindex="-1"></a><span class="co">#> • `Choice situation` -> `Choice.situation`</span></span>
+<span id="cb2-394"><a href="#cb2-394" tabindex="-1"></a><span class="co">#> • `` -> `...10`</span></span>
+<span id="cb2-395"><a href="#cb2-395" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-396"><a href="#cb2-396" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-397"><a href="#cb2-397" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-398"><a href="#cb2-398" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-399"><a href="#cb2-399" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-400"><a href="#cb2-400" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-401"><a href="#cb2-401" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-402"><a href="#cb2-402" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-403"><a href="#cb2-403" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-404"><a href="#cb2-404" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-405"><a href="#cb2-405" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-406"><a href="#cb2-406" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-407"><a href="#cb2-407" tabindex="-1"></a><span class="co">#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1</span></span>
+<span id="cb2-408"><a href="#cb2-408" tabindex="-1"></a><span class="co">#> 1 1 3 80 5.0 0.0 20 5.0 10.0 1 1 -1.150 -0.350 1.88045081 0.33059180 0.7304508</span></span>
+<span id="cb2-409"><a href="#cb2-409" tabindex="-1"></a><span class="co">#> 2 1 5 60 2.5 5.0 20 20.0 5.0 1 1 -0.675 -1.500 -0.08733163 -0.07195918 -0.7623316</span></span>
+<span id="cb2-410"><a href="#cb2-410" tabindex="-1"></a><span class="co">#> 3 1 10 80 2.5 2.5 20 20.0 0.0 1 1 -0.925 -1.600 -0.31269859 3.95512677 -1.2376986</span></span>
+<span id="cb2-411"><a href="#cb2-411" tabindex="-1"></a><span class="co">#> 4 1 34 80 2.5 5.0 60 5.0 5.0 1 1 -0.875 -0.850 0.20206751 -0.87018279 -0.6729325</span></span>
+<span id="cb2-412"><a href="#cb2-412" tabindex="-1"></a><span class="co">#> 5 1 37 40 5.0 10.0 60 5.0 2.5 1 1 -0.550 -0.900 -0.25607132 -1.21928402 -0.8060713</span></span>
+<span id="cb2-413"><a href="#cb2-413" tabindex="-1"></a><span class="co">#> 6 1 39 20 20.0 2.5 60 2.5 2.5 1 1 -1.550 -0.725 1.39833272 -0.08165078 -0.1516673</span></span>
+<span id="cb2-414"><a href="#cb2-414" tabindex="-1"></a><span class="co">#> U_2 CHOICE</span></span>
+<span id="cb2-415"><a href="#cb2-415" tabindex="-1"></a><span class="co">#> 1 -0.0194082 1</span></span>
+<span id="cb2-416"><a href="#cb2-416" tabindex="-1"></a><span class="co">#> 2 -1.5719592 1</span></span>
+<span id="cb2-417"><a href="#cb2-417" tabindex="-1"></a><span class="co">#> 3 2.3551268 2</span></span>
+<span id="cb2-418"><a href="#cb2-418" tabindex="-1"></a><span class="co">#> 4 -1.7201828 1</span></span>
+<span id="cb2-419"><a href="#cb2-419" tabindex="-1"></a><span class="co">#> 5 -2.1192840 1</span></span>
+<span id="cb2-420"><a href="#cb2-420" tabindex="-1"></a><span class="co">#> 6 -0.8066508 1</span></span>
+<span id="cb2-421"><a href="#cb2-421" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-422"><a href="#cb2-422" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-423"><a href="#cb2-423" tabindex="-1"></a><span class="co">#> This is Run number 1 </span></span>
+<span id="cb2-424"><a href="#cb2-424" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-425"><a href="#cb2-425" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-426"><a href="#cb2-426" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-427"><a href="#cb2-427" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-428"><a href="#cb2-428" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-429"><a href="#cb2-429" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-430"><a href="#cb2-430" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-431"><a href="#cb2-431" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-432"><a href="#cb2-432" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-433"><a href="#cb2-433" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-434"><a href="#cb2-434" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-435"><a href="#cb2-435" tabindex="-1"></a><span class="co">#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1</span></span>
+<span id="cb2-436"><a href="#cb2-436" tabindex="-1"></a><span class="co">#> 1 1 3 80 5.0 0.0 20 5.0 10.0 1 1 -1.150 -0.350 -0.0940785 -0.8728874 -1.24407850</span></span>
+<span id="cb2-437"><a href="#cb2-437" tabindex="-1"></a><span class="co">#> 2 1 5 60 2.5 5.0 20 20.0 5.0 1 1 -0.675 -1.500 -0.6796651 -1.1297414 -1.35466507</span></span>
+<span id="cb2-438"><a href="#cb2-438" tabindex="-1"></a><span class="co">#> 3 1 10 80 2.5 2.5 20 20.0 0.0 1 1 -0.925 -1.600 1.7899847 0.6372528 0.86498471</span></span>
+<span id="cb2-439"><a href="#cb2-439" tabindex="-1"></a><span class="co">#> 4 1 34 80 2.5 5.0 60 5.0 5.0 1 1 -0.875 -0.850 0.9429192 0.7744473 0.06791921</span></span>
+<span id="cb2-440"><a href="#cb2-440" tabindex="-1"></a><span class="co">#> 5 1 37 40 5.0 10.0 60 5.0 2.5 1 1 -0.550 -0.900 0.1003092 2.5583115 -0.44969083</span></span>
+<span id="cb2-441"><a href="#cb2-441" tabindex="-1"></a><span class="co">#> 6 1 39 20 20.0 2.5 60 2.5 2.5 1 1 -1.550 -0.725 -0.3851894 0.9776369 -1.93518939</span></span>
+<span id="cb2-442"><a href="#cb2-442" tabindex="-1"></a><span class="co">#> U_2 CHOICE</span></span>
+<span id="cb2-443"><a href="#cb2-443" tabindex="-1"></a><span class="co">#> 1 -1.22288745 2</span></span>
+<span id="cb2-444"><a href="#cb2-444" tabindex="-1"></a><span class="co">#> 2 -2.62974141 1</span></span>
+<span id="cb2-445"><a href="#cb2-445" tabindex="-1"></a><span class="co">#> 3 -0.96274717 1</span></span>
+<span id="cb2-446"><a href="#cb2-446" tabindex="-1"></a><span class="co">#> 4 -0.07555271 1</span></span>
+<span id="cb2-447"><a href="#cb2-447" tabindex="-1"></a><span class="co">#> 5 1.65831145 2</span></span>
+<span id="cb2-448"><a href="#cb2-448" tabindex="-1"></a><span class="co">#> 6 0.25263691 2</span></span>
+<span id="cb2-449"><a href="#cb2-449" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-450"><a href="#cb2-450" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-451"><a href="#cb2-451" tabindex="-1"></a><span class="co">#> This is the utility functions </span></span>
+<span id="cb2-452"><a href="#cb2-452" tabindex="-1"></a><span class="co">#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319 </span></span>
+<span id="cb2-453"><a href="#cb2-453" tabindex="-1"></a><span class="co">#> Initial gradient value:</span></span>
+<span id="cb2-454"><a href="#cb2-454" tabindex="-1"></a><span class="co">#> bpreis blade bwarte </span></span>
+<span id="cb2-455"><a href="#cb2-455" tabindex="-1"></a><span class="co">#> -2300.0 -967.5 417.5 </span></span>
+<span id="cb2-456"><a href="#cb2-456" tabindex="-1"></a><span class="co">#> initial value 998.131940 </span></span>
+<span id="cb2-457"><a href="#cb2-457" tabindex="-1"></a><span class="co">#> iter 2 value 989.783897</span></span>
+<span id="cb2-458"><a href="#cb2-458" tabindex="-1"></a><span class="co">#> iter 3 value 967.441065</span></span>
+<span id="cb2-459"><a href="#cb2-459" tabindex="-1"></a><span class="co">#> iter 4 value 966.807343</span></span>
+<span id="cb2-460"><a href="#cb2-460" tabindex="-1"></a><span class="co">#> iter 5 value 957.535574</span></span>
+<span id="cb2-461"><a href="#cb2-461" tabindex="-1"></a><span class="co">#> iter 6 value 957.518843</span></span>
+<span id="cb2-462"><a href="#cb2-462" tabindex="-1"></a><span class="co">#> iter 7 value 957.518805</span></span>
+<span id="cb2-463"><a href="#cb2-463" tabindex="-1"></a><span class="co">#> iter 7 value 957.518805</span></span>
+<span id="cb2-464"><a href="#cb2-464" tabindex="-1"></a><span class="co">#> iter 7 value 957.518805</span></span>
+<span id="cb2-465"><a href="#cb2-465" tabindex="-1"></a><span class="co">#> final value 957.518805 </span></span>
+<span id="cb2-466"><a href="#cb2-466" tabindex="-1"></a><span class="co">#> converged</span></span>
+<span id="cb2-467"><a href="#cb2-467" tabindex="-1"></a><span class="co">#> This is Run number 2 </span></span>
+<span id="cb2-468"><a href="#cb2-468" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-469"><a href="#cb2-469" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-470"><a href="#cb2-470" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-471"><a href="#cb2-471" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-472"><a href="#cb2-472" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-473"><a href="#cb2-473" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-474"><a href="#cb2-474" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-475"><a href="#cb2-475" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-476"><a href="#cb2-476" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-477"><a href="#cb2-477" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-478"><a href="#cb2-478" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-479"><a href="#cb2-479" tabindex="-1"></a><span class="co">#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1</span></span>
+<span id="cb2-480"><a href="#cb2-480" tabindex="-1"></a><span class="co">#> 1 1 3 80 5.0 0.0 20 5.0 10.0 1 1 -1.150 -0.350 0.39615659 0.74248610 -0.7538434</span></span>
+<span id="cb2-481"><a href="#cb2-481" tabindex="-1"></a><span class="co">#> 2 1 5 60 2.5 5.0 20 20.0 5.0 1 1 -0.675 -1.500 -0.17578286 0.04260786 -0.8507829</span></span>
+<span id="cb2-482"><a href="#cb2-482" tabindex="-1"></a><span class="co">#> 3 1 10 80 2.5 2.5 20 20.0 0.0 1 1 -0.925 -1.600 0.44905385 0.79514566 -0.4759461</span></span>
+<span id="cb2-483"><a href="#cb2-483" tabindex="-1"></a><span class="co">#> 4 1 34 80 2.5 5.0 60 5.0 5.0 1 1 -0.875 -0.850 0.27140789 4.63953174 -0.6035921</span></span>
+<span id="cb2-484"><a href="#cb2-484" tabindex="-1"></a><span class="co">#> 5 1 37 40 5.0 10.0 60 5.0 2.5 1 1 -0.550 -0.900 -0.03370054 0.84622952 -0.5837005</span></span>
+<span id="cb2-485"><a href="#cb2-485" tabindex="-1"></a><span class="co">#> 6 1 39 20 20.0 2.5 60 2.5 2.5 1 1 -1.550 -0.725 -0.47233862 1.05805421 -2.0223386</span></span>
+<span id="cb2-486"><a href="#cb2-486" tabindex="-1"></a><span class="co">#> U_2 CHOICE</span></span>
+<span id="cb2-487"><a href="#cb2-487" tabindex="-1"></a><span class="co">#> 1 0.39248610 2</span></span>
+<span id="cb2-488"><a href="#cb2-488" tabindex="-1"></a><span class="co">#> 2 -1.45739214 1</span></span>
+<span id="cb2-489"><a href="#cb2-489" tabindex="-1"></a><span class="co">#> 3 -0.80485434 1</span></span>
+<span id="cb2-490"><a href="#cb2-490" tabindex="-1"></a><span class="co">#> 4 3.78953174 2</span></span>
+<span id="cb2-491"><a href="#cb2-491" tabindex="-1"></a><span class="co">#> 5 -0.05377048 2</span></span>
+<span id="cb2-492"><a href="#cb2-492" tabindex="-1"></a><span class="co">#> 6 0.33305421 2</span></span>
+<span id="cb2-493"><a href="#cb2-493" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-494"><a href="#cb2-494" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-495"><a href="#cb2-495" tabindex="-1"></a><span class="co">#> This is the utility functions </span></span>
+<span id="cb2-496"><a href="#cb2-496" tabindex="-1"></a><span class="co">#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319 </span></span>
+<span id="cb2-497"><a href="#cb2-497" tabindex="-1"></a><span class="co">#> Initial gradient value:</span></span>
+<span id="cb2-498"><a href="#cb2-498" tabindex="-1"></a><span class="co">#> bpreis blade bwarte </span></span>
+<span id="cb2-499"><a href="#cb2-499" tabindex="-1"></a><span class="co">#> -1600.0 -857.5 402.5 </span></span>
+<span id="cb2-500"><a href="#cb2-500" tabindex="-1"></a><span class="co">#> initial value 998.131940 </span></span>
+<span id="cb2-501"><a href="#cb2-501" tabindex="-1"></a><span class="co">#> iter 2 value 993.094191</span></span>
+<span id="cb2-502"><a href="#cb2-502" tabindex="-1"></a><span class="co">#> iter 3 value 975.977284</span></span>
+<span id="cb2-503"><a href="#cb2-503" tabindex="-1"></a><span class="co">#> iter 4 value 975.860148</span></span>
+<span id="cb2-504"><a href="#cb2-504" tabindex="-1"></a><span class="co">#> iter 5 value 971.032264</span></span>
+<span id="cb2-505"><a href="#cb2-505" tabindex="-1"></a><span class="co">#> iter 6 value 971.027871</span></span>
+<span id="cb2-506"><a href="#cb2-506" tabindex="-1"></a><span class="co">#> iter 6 value 971.027867</span></span>
+<span id="cb2-507"><a href="#cb2-507" tabindex="-1"></a><span class="co">#> iter 6 value 971.027867</span></span>
+<span id="cb2-508"><a href="#cb2-508" tabindex="-1"></a><span class="co">#> final value 971.027867 </span></span>
+<span id="cb2-509"><a href="#cb2-509" tabindex="-1"></a><span class="co">#> converged</span></span>
+<span id="cb2-510"><a href="#cb2-510" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-511"><a href="#cb2-511" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-512"><a href="#cb2-512" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-513"><a href="#cb2-513" tabindex="-1"></a><span class="co">#> \ vars n mean sd min max range se</span></span>
+<span id="cb2-514"><a href="#cb2-514" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-515"><a href="#cb2-515" tabindex="-1"></a><span class="co">#> est_bpreis 1 2 -0.01 0.00 -0.01 -0.01 0.00 0.00</span></span>
+<span id="cb2-516"><a href="#cb2-516" tabindex="-1"></a><span class="co">#> est_blade 2 2 -0.05 0.01 -0.05 -0.04 0.01 0.01</span></span>
+<span id="cb2-517"><a href="#cb2-517" tabindex="-1"></a><span class="co">#> est_bwarte 3 2 0.00 0.01 0.00 0.01 0.01 0.00</span></span>
+<span id="cb2-518"><a href="#cb2-518" tabindex="-1"></a><span class="co">#> rob_pval0_bpreis 4 2 0.00 0.00 0.00 0.00 0.00 0.00</span></span>
+<span id="cb2-519"><a href="#cb2-519" tabindex="-1"></a><span class="co">#> rob_pval0_blade 5 2 0.00 0.00 0.00 0.00 0.00 0.00</span></span>
+<span id="cb2-520"><a href="#cb2-520" tabindex="-1"></a><span class="co">#> rob_pval0_bwarte 6 2 0.68 0.20 0.54 0.82 0.28 0.14</span></span>
+<span id="cb2-521"><a href="#cb2-521" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-522"><a href="#cb2-522" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-523"><a href="#cb2-523" tabindex="-1"></a><span class="co">#> FALSE </span></span>
+<span id="cb2-524"><a href="#cb2-524" tabindex="-1"></a><span class="co">#> 100 </span></span>
+<span id="cb2-525"><a href="#cb2-525" tabindex="-1"></a><span class="co">#> Utility function used in simulation, ie the true utility: </span></span>
+<span id="cb2-526"><a href="#cb2-526" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-527"><a href="#cb2-527" tabindex="-1"></a><span class="co">#> $u1</span></span>
+<span id="cb2-528"><a href="#cb2-528" tabindex="-1"></a><span class="co">#> $u1$v1</span></span>
+<span id="cb2-529"><a href="#cb2-529" tabindex="-1"></a><span class="co">#> V.1 ~ bpreis * alt1.x1 + blade * alt1.x2 + bwarte * alt1.x3</span></span>
+<span id="cb2-530"><a href="#cb2-530" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-531"><a href="#cb2-531" tabindex="-1"></a><span class="co">#> $u1$v2</span></span>
+<span id="cb2-532"><a href="#cb2-532" tabindex="-1"></a><span class="co">#> V.2 ~ bpreis * alt2.x1 + blade * alt2.x2 + bwarte * alt2.x3</span></span>
+<span id="cb2-533"><a href="#cb2-533" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-534"><a href="#cb2-534" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-535"><a href="#cb2-535" tabindex="-1"></a><span class="co">#> $u2</span></span>
+<span id="cb2-536"><a href="#cb2-536" tabindex="-1"></a><span class="co">#> $u2$v1</span></span>
+<span id="cb2-537"><a href="#cb2-537" tabindex="-1"></a><span class="co">#> V.1 ~ bpreis * alt1.x1</span></span>
+<span id="cb2-538"><a href="#cb2-538" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-539"><a href="#cb2-539" tabindex="-1"></a><span class="co">#> $u2$v2</span></span>
+<span id="cb2-540"><a href="#cb2-540" tabindex="-1"></a><span class="co">#> V.2 ~ bpreis * alt2.x1</span></span>
+<span id="cb2-541"><a href="#cb2-541" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-542"><a href="#cb2-542" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-543"><a href="#cb2-543" tabindex="-1"></a><span class="co">#> Utility function used for Logit estimation with mixl: </span></span>
+<span id="cb2-544"><a href="#cb2-544" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-545"><a href="#cb2-545" tabindex="-1"></a><span class="co">#> [1] "U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;"</span></span>
+<span id="cb2-546"><a href="#cb2-546" tabindex="-1"></a><span class="co">#> New names:</span></span>
+<span id="cb2-547"><a href="#cb2-547" tabindex="-1"></a><span class="co">#> • `Choice situation` -> `Choice.situation`</span></span>
+<span id="cb2-548"><a href="#cb2-548" tabindex="-1"></a><span class="co">#> • `` -> `...10`</span></span>
+<span id="cb2-549"><a href="#cb2-549" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-550"><a href="#cb2-550" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-551"><a href="#cb2-551" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-552"><a href="#cb2-552" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-553"><a href="#cb2-553" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-554"><a href="#cb2-554" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-555"><a href="#cb2-555" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-556"><a href="#cb2-556" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-557"><a href="#cb2-557" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-558"><a href="#cb2-558" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-559"><a href="#cb2-559" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-560"><a href="#cb2-560" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-561"><a href="#cb2-561" tabindex="-1"></a><span class="co">#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2</span></span>
+<span id="cb2-562"><a href="#cb2-562" tabindex="-1"></a><span class="co">#> 1 1 9 80 5.0 0 60 20.0 10.0 1 1 -1.150 -1.800 0.8053210 -0.7760447 -0.34467900 -2.5760447</span></span>
+<span id="cb2-563"><a href="#cb2-563" tabindex="-1"></a><span class="co">#> 2 1 12 60 2.5 10 40 20.0 0.0 1 1 -0.575 -1.800 2.4581484 -0.5422855 1.88314842 -2.3422855</span></span>
+<span id="cb2-564"><a href="#cb2-564" tabindex="-1"></a><span class="co">#> 3 1 13 20 20.0 10 80 2.5 0.0 1 1 -1.400 -0.975 0.4806134 -1.7030310 -0.91938664 -2.6780310</span></span>
+<span id="cb2-565"><a href="#cb2-565" tabindex="-1"></a><span class="co">#> 4 1 70 80 5.0 10 20 20.0 2.5 1 1 -0.950 -1.550 -0.8558539 1.9784273 -1.80585392 0.4284273</span></span>
+<span id="cb2-566"><a href="#cb2-566" tabindex="-1"></a><span class="co">#> 5 1 71 60 20.0 10 80 10.0 0.0 1 1 -1.800 -1.500 1.4200481 0.8856199 -0.37995187 -0.6143801</span></span>
+<span id="cb2-567"><a href="#cb2-567" tabindex="-1"></a><span class="co">#> 6 1 73 60 10.0 0 40 20.0 10.0 1 1 -1.300 -1.600 1.3592506 -0.1823192 0.05925063 -1.7823192</span></span>
+<span id="cb2-568"><a href="#cb2-568" tabindex="-1"></a><span class="co">#> CHOICE</span></span>
+<span id="cb2-569"><a href="#cb2-569" tabindex="-1"></a><span class="co">#> 1 1</span></span>
+<span id="cb2-570"><a href="#cb2-570" tabindex="-1"></a><span class="co">#> 2 1</span></span>
+<span id="cb2-571"><a href="#cb2-571" tabindex="-1"></a><span class="co">#> 3 1</span></span>
+<span id="cb2-572"><a href="#cb2-572" tabindex="-1"></a><span class="co">#> 4 2</span></span>
+<span id="cb2-573"><a href="#cb2-573" tabindex="-1"></a><span class="co">#> 5 1</span></span>
+<span id="cb2-574"><a href="#cb2-574" tabindex="-1"></a><span class="co">#> 6 1</span></span>
+<span id="cb2-575"><a href="#cb2-575" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-576"><a href="#cb2-576" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-577"><a href="#cb2-577" tabindex="-1"></a><span class="co">#> This is Run number 1 </span></span>
+<span id="cb2-578"><a href="#cb2-578" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-579"><a href="#cb2-579" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-580"><a href="#cb2-580" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-581"><a href="#cb2-581" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-582"><a href="#cb2-582" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-583"><a href="#cb2-583" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-584"><a href="#cb2-584" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-585"><a href="#cb2-585" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-586"><a href="#cb2-586" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-587"><a href="#cb2-587" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-588"><a href="#cb2-588" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-589"><a href="#cb2-589" tabindex="-1"></a><span class="co">#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2</span></span>
+<span id="cb2-590"><a href="#cb2-590" tabindex="-1"></a><span class="co">#> 1 1 9 80 5.0 0 60 20.0 10.0 1 1 -1.150 -1.800 1.1057596 0.8176933 -0.04424039 -0.9823067</span></span>
+<span id="cb2-591"><a href="#cb2-591" tabindex="-1"></a><span class="co">#> 2 1 12 60 2.5 10 40 20.0 0.0 1 1 -0.575 -1.800 1.4664332 0.2855647 0.89143319 -1.5144353</span></span>
+<span id="cb2-592"><a href="#cb2-592" tabindex="-1"></a><span class="co">#> 3 1 13 20 20.0 10 80 2.5 0.0 1 1 -1.400 -0.975 -0.2567456 2.0307365 -1.65674558 1.0557365</span></span>
+<span id="cb2-593"><a href="#cb2-593" tabindex="-1"></a><span class="co">#> 4 1 70 80 5.0 10 20 20.0 2.5 1 1 -0.950 -1.550 1.7936733 0.2273817 0.84367334 -1.3226183</span></span>
+<span id="cb2-594"><a href="#cb2-594" tabindex="-1"></a><span class="co">#> 5 1 71 60 20.0 10 80 10.0 0.0 1 1 -1.800 -1.500 -0.5080847 1.8371868 -2.30808468 0.3371868</span></span>
+<span id="cb2-595"><a href="#cb2-595" tabindex="-1"></a><span class="co">#> 6 1 73 60 10.0 0 40 20.0 10.0 1 1 -1.300 -1.600 0.2315646 0.5250324 -1.06843538 -1.0749676</span></span>
+<span id="cb2-596"><a href="#cb2-596" tabindex="-1"></a><span class="co">#> CHOICE</span></span>
+<span id="cb2-597"><a href="#cb2-597" tabindex="-1"></a><span class="co">#> 1 1</span></span>
+<span id="cb2-598"><a href="#cb2-598" tabindex="-1"></a><span class="co">#> 2 1</span></span>
+<span id="cb2-599"><a href="#cb2-599" tabindex="-1"></a><span class="co">#> 3 2</span></span>
+<span id="cb2-600"><a href="#cb2-600" tabindex="-1"></a><span class="co">#> 4 1</span></span>
+<span id="cb2-601"><a href="#cb2-601" tabindex="-1"></a><span class="co">#> 5 2</span></span>
+<span id="cb2-602"><a href="#cb2-602" tabindex="-1"></a><span class="co">#> 6 1</span></span>
+<span id="cb2-603"><a href="#cb2-603" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-604"><a href="#cb2-604" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-605"><a href="#cb2-605" tabindex="-1"></a><span class="co">#> This is the utility functions </span></span>
+<span id="cb2-606"><a href="#cb2-606" tabindex="-1"></a><span class="co">#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319 </span></span>
+<span id="cb2-607"><a href="#cb2-607" tabindex="-1"></a><span class="co">#> Initial gradient value:</span></span>
+<span id="cb2-608"><a href="#cb2-608" tabindex="-1"></a><span class="co">#> bpreis blade bwarte </span></span>
+<span id="cb2-609"><a href="#cb2-609" tabindex="-1"></a><span class="co">#> -2720.0 -3230.0 1477.5 </span></span>
+<span id="cb2-610"><a href="#cb2-610" tabindex="-1"></a><span class="co">#> initial value 998.131940 </span></span>
+<span id="cb2-611"><a href="#cb2-611" tabindex="-1"></a><span class="co">#> iter 2 value 961.903346</span></span>
+<span id="cb2-612"><a href="#cb2-612" tabindex="-1"></a><span class="co">#> iter 3 value 923.013503</span></span>
+<span id="cb2-613"><a href="#cb2-613" tabindex="-1"></a><span class="co">#> iter 4 value 921.553693</span></span>
+<span id="cb2-614"><a href="#cb2-614" tabindex="-1"></a><span class="co">#> iter 5 value 899.826852</span></span>
+<span id="cb2-615"><a href="#cb2-615" tabindex="-1"></a><span class="co">#> iter 6 value 899.416093</span></span>
+<span id="cb2-616"><a href="#cb2-616" tabindex="-1"></a><span class="co">#> iter 7 value 899.408733</span></span>
+<span id="cb2-617"><a href="#cb2-617" tabindex="-1"></a><span class="co">#> iter 7 value 899.408728</span></span>
+<span id="cb2-618"><a href="#cb2-618" tabindex="-1"></a><span class="co">#> iter 7 value 899.408728</span></span>
+<span id="cb2-619"><a href="#cb2-619" tabindex="-1"></a><span class="co">#> final value 899.408728 </span></span>
+<span id="cb2-620"><a href="#cb2-620" tabindex="-1"></a><span class="co">#> converged</span></span>
+<span id="cb2-621"><a href="#cb2-621" tabindex="-1"></a><span class="co">#> This is Run number 2 </span></span>
+<span id="cb2-622"><a href="#cb2-622" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-623"><a href="#cb2-623" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-624"><a href="#cb2-624" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-625"><a href="#cb2-625" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-626"><a href="#cb2-626" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-627"><a href="#cb2-627" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-628"><a href="#cb2-628" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-629"><a href="#cb2-629" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-630"><a href="#cb2-630" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-631"><a href="#cb2-631" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-632"><a href="#cb2-632" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-633"><a href="#cb2-633" tabindex="-1"></a><span class="co">#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2</span></span>
+<span id="cb2-634"><a href="#cb2-634" tabindex="-1"></a><span class="co">#> 1 1 9 80 5.0 0 60 20.0 10.0 1 1 -1.150 -1.800 -0.55606335 0.4418297 -1.7060633 -1.3581703</span></span>
+<span id="cb2-635"><a href="#cb2-635" tabindex="-1"></a><span class="co">#> 2 1 12 60 2.5 10 40 20.0 0.0 1 1 -0.575 -1.800 -0.70525965 0.3030154 -1.2802596 -1.4969846</span></span>
+<span id="cb2-636"><a href="#cb2-636" tabindex="-1"></a><span class="co">#> 3 1 13 20 20.0 10 80 2.5 0.0 1 1 -1.400 -0.975 0.76358526 1.1547805 -0.6364147 0.1797805</span></span>
+<span id="cb2-637"><a href="#cb2-637" tabindex="-1"></a><span class="co">#> 4 1 70 80 5.0 10 20 20.0 2.5 1 1 -0.950 -1.550 -0.50057341 1.6569802 -1.4505734 0.1069802</span></span>
+<span id="cb2-638"><a href="#cb2-638" tabindex="-1"></a><span class="co">#> 5 1 71 60 20.0 10 80 10.0 0.0 1 1 -1.800 -1.500 0.95196390 4.6640005 -0.8480361 3.1640005</span></span>
+<span id="cb2-639"><a href="#cb2-639" tabindex="-1"></a><span class="co">#> 6 1 73 60 10.0 0 40 20.0 10.0 1 1 -1.300 -1.600 -0.07807331 0.9519585 -1.3780733 -0.6480415</span></span>
+<span id="cb2-640"><a href="#cb2-640" tabindex="-1"></a><span class="co">#> CHOICE</span></span>
+<span id="cb2-641"><a href="#cb2-641" tabindex="-1"></a><span class="co">#> 1 2</span></span>
+<span id="cb2-642"><a href="#cb2-642" tabindex="-1"></a><span class="co">#> 2 1</span></span>
+<span id="cb2-643"><a href="#cb2-643" tabindex="-1"></a><span class="co">#> 3 2</span></span>
+<span id="cb2-644"><a href="#cb2-644" tabindex="-1"></a><span class="co">#> 4 2</span></span>
+<span id="cb2-645"><a href="#cb2-645" tabindex="-1"></a><span class="co">#> 5 2</span></span>
+<span id="cb2-646"><a href="#cb2-646" tabindex="-1"></a><span class="co">#> 6 2</span></span>
+<span id="cb2-647"><a href="#cb2-647" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-648"><a href="#cb2-648" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-649"><a href="#cb2-649" tabindex="-1"></a><span class="co">#> This is the utility functions </span></span>
+<span id="cb2-650"><a href="#cb2-650" tabindex="-1"></a><span class="co">#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319 </span></span>
+<span id="cb2-651"><a href="#cb2-651" tabindex="-1"></a><span class="co">#> Initial gradient value:</span></span>
+<span id="cb2-652"><a href="#cb2-652" tabindex="-1"></a><span class="co">#> bpreis blade bwarte </span></span>
+<span id="cb2-653"><a href="#cb2-653" tabindex="-1"></a><span class="co">#> -1480.0 -3742.5 752.5 </span></span>
+<span id="cb2-654"><a href="#cb2-654" tabindex="-1"></a><span class="co">#> initial value 998.131940 </span></span>
+<span id="cb2-655"><a href="#cb2-655" tabindex="-1"></a><span class="co">#> iter 2 value 931.326512</span></span>
+<span id="cb2-656"><a href="#cb2-656" tabindex="-1"></a><span class="co">#> iter 3 value 904.389362</span></span>
+<span id="cb2-657"><a href="#cb2-657" tabindex="-1"></a><span class="co">#> iter 4 value 902.747564</span></span>
+<span id="cb2-658"><a href="#cb2-658" tabindex="-1"></a><span class="co">#> iter 5 value 895.585146</span></span>
+<span id="cb2-659"><a href="#cb2-659" tabindex="-1"></a><span class="co">#> iter 6 value 895.212841</span></span>
+<span id="cb2-660"><a href="#cb2-660" tabindex="-1"></a><span class="co">#> iter 7 value 895.208094</span></span>
+<span id="cb2-661"><a href="#cb2-661" tabindex="-1"></a><span class="co">#> iter 7 value 895.208091</span></span>
+<span id="cb2-662"><a href="#cb2-662" tabindex="-1"></a><span class="co">#> iter 7 value 895.208091</span></span>
+<span id="cb2-663"><a href="#cb2-663" tabindex="-1"></a><span class="co">#> final value 895.208091 </span></span>
+<span id="cb2-664"><a href="#cb2-664" tabindex="-1"></a><span class="co">#> converged</span></span>
+<span id="cb2-665"><a href="#cb2-665" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-666"><a href="#cb2-666" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-667"><a href="#cb2-667" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-668"><a href="#cb2-668" tabindex="-1"></a><span class="co">#> \ vars n mean sd min max range se</span></span>
+<span id="cb2-669"><a href="#cb2-669" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-670"><a href="#cb2-670" tabindex="-1"></a><span class="co">#> est_bpreis 1 2 -0.01 0.00 -0.01 -0.01 0.00 0.00</span></span>
+<span id="cb2-671"><a href="#cb2-671" tabindex="-1"></a><span class="co">#> est_blade 2 2 -0.05 0.01 -0.05 -0.04 0.01 0.01</span></span>
+<span id="cb2-672"><a href="#cb2-672" tabindex="-1"></a><span class="co">#> est_bwarte 3 2 0.01 0.03 0.00 0.03 0.04 0.02</span></span>
+<span id="cb2-673"><a href="#cb2-673" tabindex="-1"></a><span class="co">#> rob_pval0_bpreis 4 2 0.00 0.00 0.00 0.00 0.00 0.00</span></span>
+<span id="cb2-674"><a href="#cb2-674" tabindex="-1"></a><span class="co">#> rob_pval0_blade 5 2 0.00 0.00 0.00 0.00 0.00 0.00</span></span>
+<span id="cb2-675"><a href="#cb2-675" tabindex="-1"></a><span class="co">#> rob_pval0_bwarte 6 2 0.28 0.40 0.00 0.57 0.57 0.28</span></span>
+<span id="cb2-676"><a href="#cb2-676" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-677"><a href="#cb2-677" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-678"><a href="#cb2-678" tabindex="-1"></a><span class="co">#> FALSE TRUE </span></span>
+<span id="cb2-679"><a href="#cb2-679" tabindex="-1"></a><span class="co">#> 50 50 </span></span>
+<span id="cb2-680"><a href="#cb2-680" tabindex="-1"></a><span class="co">#> Utility function used in simulation, ie the true utility: </span></span>
+<span id="cb2-681"><a href="#cb2-681" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-682"><a href="#cb2-682" tabindex="-1"></a><span class="co">#> $u1</span></span>
+<span id="cb2-683"><a href="#cb2-683" tabindex="-1"></a><span class="co">#> $u1$v1</span></span>
+<span id="cb2-684"><a href="#cb2-684" tabindex="-1"></a><span class="co">#> V.1 ~ bpreis * alt1.x1 + blade * alt1.x2 + bwarte * alt1.x3</span></span>
+<span id="cb2-685"><a href="#cb2-685" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-686"><a href="#cb2-686" tabindex="-1"></a><span class="co">#> $u1$v2</span></span>
+<span id="cb2-687"><a href="#cb2-687" tabindex="-1"></a><span class="co">#> V.2 ~ bpreis * alt2.x1 + blade * alt2.x2 + bwarte * alt2.x3</span></span>
+<span id="cb2-688"><a href="#cb2-688" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-689"><a href="#cb2-689" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-690"><a href="#cb2-690" tabindex="-1"></a><span class="co">#> $u2</span></span>
+<span id="cb2-691"><a href="#cb2-691" tabindex="-1"></a><span class="co">#> $u2$v1</span></span>
+<span id="cb2-692"><a href="#cb2-692" tabindex="-1"></a><span class="co">#> V.1 ~ bpreis * alt1.x1</span></span>
+<span id="cb2-693"><a href="#cb2-693" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-694"><a href="#cb2-694" tabindex="-1"></a><span class="co">#> $u2$v2</span></span>
+<span id="cb2-695"><a href="#cb2-695" tabindex="-1"></a><span class="co">#> V.2 ~ bpreis * alt2.x1</span></span>
+<span id="cb2-696"><a href="#cb2-696" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-697"><a href="#cb2-697" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-698"><a href="#cb2-698" tabindex="-1"></a><span class="co">#> Utility function used for Logit estimation with mixl: </span></span>
+<span id="cb2-699"><a href="#cb2-699" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-700"><a href="#cb2-700" tabindex="-1"></a><span class="co">#> [1] "U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;"</span></span>
+<span id="cb2-701"><a href="#cb2-701" tabindex="-1"></a><span class="co">#> New names:</span></span>
+<span id="cb2-702"><a href="#cb2-702" tabindex="-1"></a><span class="co">#> • `Choice situation` -> `Choice.situation`</span></span>
+<span id="cb2-703"><a href="#cb2-703" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-704"><a href="#cb2-704" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-705"><a href="#cb2-705" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-706"><a href="#cb2-706" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-707"><a href="#cb2-707" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-708"><a href="#cb2-708" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-709"><a href="#cb2-709" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-710"><a href="#cb2-710" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-711"><a href="#cb2-711" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-712"><a href="#cb2-712" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-713"><a href="#cb2-713" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-714"><a href="#cb2-714" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-715"><a href="#cb2-715" tabindex="-1"></a><span class="co">#> ID Choice_situation Block alt1_x1 alt2_x1 alt1_x2 alt2_x2 alt1_x3 alt2_x3 group V_1 V_2 e_1 e_2 U_1 U_2</span></span>
+<span id="cb2-716"><a href="#cb2-716" tabindex="-1"></a><span class="co">#> 1 1 1 1 80 20 2.5 20.0 10 5 1 -0.775 -1.500 0.12234341 0.6503776 -0.6526566 -0.84962241</span></span>
+<span id="cb2-717"><a href="#cb2-717" tabindex="-1"></a><span class="co">#> 2 1 2 1 60 40 5.0 10.0 5 10 1 -0.850 -0.900 -0.43360819 0.6615210 -1.2836082 -0.23847900</span></span>
+<span id="cb2-718"><a href="#cb2-718" tabindex="-1"></a><span class="co">#> 3 1 3 1 60 20 20.0 20.0 0 10 1 -2.000 -1.400 -0.31286639 5.7827787 -2.3128664 4.38277870</span></span>
+<span id="cb2-719"><a href="#cb2-719" tabindex="-1"></a><span class="co">#> 4 1 4 1 20 80 20.0 2.5 0 10 1 -1.600 -0.775 -0.15949911 0.6857678 -1.7594991 -0.08923219</span></span>
+<span id="cb2-720"><a href="#cb2-720" tabindex="-1"></a><span class="co">#> 5 1 5 1 40 80 10.0 5.0 10 5 1 -0.900 -1.050 -0.05237788 1.5859039 -0.9523779 0.53590389</span></span>
+<span id="cb2-721"><a href="#cb2-721" tabindex="-1"></a><span class="co">#> 6 1 6 1 60 80 5.0 2.5 0 0 1 -0.950 -0.975 2.34036634 0.2393918 1.3903663 -0.73560816</span></span>
+<span id="cb2-722"><a href="#cb2-722" tabindex="-1"></a><span class="co">#> CHOICE</span></span>
+<span id="cb2-723"><a href="#cb2-723" tabindex="-1"></a><span class="co">#> 1 1</span></span>
+<span id="cb2-724"><a href="#cb2-724" tabindex="-1"></a><span class="co">#> 2 2</span></span>
+<span id="cb2-725"><a href="#cb2-725" tabindex="-1"></a><span class="co">#> 3 2</span></span>
+<span id="cb2-726"><a href="#cb2-726" tabindex="-1"></a><span class="co">#> 4 2</span></span>
+<span id="cb2-727"><a href="#cb2-727" tabindex="-1"></a><span class="co">#> 5 2</span></span>
+<span id="cb2-728"><a href="#cb2-728" tabindex="-1"></a><span class="co">#> 6 1</span></span>
+<span id="cb2-729"><a href="#cb2-729" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-730"><a href="#cb2-730" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-731"><a href="#cb2-731" tabindex="-1"></a><span class="co">#> This is Run number 1 </span></span>
+<span id="cb2-732"><a href="#cb2-732" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-733"><a href="#cb2-733" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-734"><a href="#cb2-734" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-735"><a href="#cb2-735" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-736"><a href="#cb2-736" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-737"><a href="#cb2-737" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-738"><a href="#cb2-738" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-739"><a href="#cb2-739" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-740"><a href="#cb2-740" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-741"><a href="#cb2-741" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-742"><a href="#cb2-742" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-743"><a href="#cb2-743" tabindex="-1"></a><span class="co">#> ID Choice_situation Block alt1_x1 alt2_x1 alt1_x2 alt2_x2 alt1_x3 alt2_x3 group V_1 V_2 e_1 e_2 U_1</span></span>
+<span id="cb2-744"><a href="#cb2-744" tabindex="-1"></a><span class="co">#> 1 1 1 1 80 20 2.5 20.0 10 5 1 -0.775 -1.500 1.74395858 1.6507121 0.968958575</span></span>
+<span id="cb2-745"><a href="#cb2-745" tabindex="-1"></a><span class="co">#> 2 1 2 1 60 40 5.0 10.0 5 10 1 -0.850 -0.900 1.10763894 0.9337414 0.257638936</span></span>
+<span id="cb2-746"><a href="#cb2-746" tabindex="-1"></a><span class="co">#> 3 1 3 1 60 20 20.0 20.0 0 10 1 -2.000 -1.400 -1.23519031 -0.7089281 -3.235190315</span></span>
+<span id="cb2-747"><a href="#cb2-747" tabindex="-1"></a><span class="co">#> 4 1 4 1 20 80 20.0 2.5 0 10 1 -1.600 -0.775 -0.06854059 2.1896932 -1.668540589</span></span>
+<span id="cb2-748"><a href="#cb2-748" tabindex="-1"></a><span class="co">#> 5 1 5 1 40 80 10.0 5.0 10 5 1 -0.900 -1.050 0.90927543 0.3884170 0.009275432</span></span>
+<span id="cb2-749"><a href="#cb2-749" tabindex="-1"></a><span class="co">#> 6 1 6 1 60 80 5.0 2.5 0 0 1 -0.950 -0.975 0.57272851 0.4992305 -0.377271490</span></span>
+<span id="cb2-750"><a href="#cb2-750" tabindex="-1"></a><span class="co">#> U_2 CHOICE</span></span>
+<span id="cb2-751"><a href="#cb2-751" tabindex="-1"></a><span class="co">#> 1 0.15071215 1</span></span>
+<span id="cb2-752"><a href="#cb2-752" tabindex="-1"></a><span class="co">#> 2 0.03374141 1</span></span>
+<span id="cb2-753"><a href="#cb2-753" tabindex="-1"></a><span class="co">#> 3 -2.10892809 2</span></span>
+<span id="cb2-754"><a href="#cb2-754" tabindex="-1"></a><span class="co">#> 4 1.41469320 2</span></span>
+<span id="cb2-755"><a href="#cb2-755" tabindex="-1"></a><span class="co">#> 5 -0.66158301 1</span></span>
+<span id="cb2-756"><a href="#cb2-756" tabindex="-1"></a><span class="co">#> 6 -0.47576952 1</span></span>
+<span id="cb2-757"><a href="#cb2-757" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-758"><a href="#cb2-758" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-759"><a href="#cb2-759" tabindex="-1"></a><span class="co">#> This is the utility functions </span></span>
+<span id="cb2-760"><a href="#cb2-760" tabindex="-1"></a><span class="co">#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319 </span></span>
+<span id="cb2-761"><a href="#cb2-761" tabindex="-1"></a><span class="co">#> Initial gradient value:</span></span>
+<span id="cb2-762"><a href="#cb2-762" tabindex="-1"></a><span class="co">#> bpreis blade bwarte </span></span>
+<span id="cb2-763"><a href="#cb2-763" tabindex="-1"></a><span class="co">#> -880 -830 405 </span></span>
+<span id="cb2-764"><a href="#cb2-764" tabindex="-1"></a><span class="co">#> initial value 998.131940 </span></span>
+<span id="cb2-765"><a href="#cb2-765" tabindex="-1"></a><span class="co">#> iter 2 value 994.862696</span></span>
+<span id="cb2-766"><a href="#cb2-766" tabindex="-1"></a><span class="co">#> iter 3 value 973.696602</span></span>
+<span id="cb2-767"><a href="#cb2-767" tabindex="-1"></a><span class="co">#> iter 4 value 973.644209</span></span>
+<span id="cb2-768"><a href="#cb2-768" tabindex="-1"></a><span class="co">#> iter 5 value 971.118222</span></span>
+<span id="cb2-769"><a href="#cb2-769" tabindex="-1"></a><span class="co">#> iter 6 value 971.113908</span></span>
+<span id="cb2-770"><a href="#cb2-770" tabindex="-1"></a><span class="co">#> iter 6 value 971.113906</span></span>
+<span id="cb2-771"><a href="#cb2-771" tabindex="-1"></a><span class="co">#> iter 6 value 971.113906</span></span>
+<span id="cb2-772"><a href="#cb2-772" tabindex="-1"></a><span class="co">#> final value 971.113906 </span></span>
+<span id="cb2-773"><a href="#cb2-773" tabindex="-1"></a><span class="co">#> converged</span></span>
+<span id="cb2-774"><a href="#cb2-774" tabindex="-1"></a><span class="co">#> This is Run number 2 </span></span>
+<span id="cb2-775"><a href="#cb2-775" tabindex="-1"></a><span class="co">#> does sou_gis exist: FALSE </span></span>
+<span id="cb2-776"><a href="#cb2-776" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-777"><a href="#cb2-777" tabindex="-1"></a><span class="co">#> dataset final_set exists: FALSE </span></span>
+<span id="cb2-778"><a href="#cb2-778" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-779"><a href="#cb2-779" tabindex="-1"></a><span class="co">#> decisiongroups exists: TRUE</span></span>
+<span id="cb2-780"><a href="#cb2-780" tabindex="-1"></a><span class="co">#> 1 2 </span></span>
+<span id="cb2-781"><a href="#cb2-781" tabindex="-1"></a><span class="co">#> 1007 433 </span></span>
+<span id="cb2-782"><a href="#cb2-782" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-783"><a href="#cb2-783" tabindex="-1"></a><span class="co">#> data has been made </span></span>
+<span id="cb2-784"><a href="#cb2-784" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-785"><a href="#cb2-785" tabindex="-1"></a><span class="co">#> First few observations </span></span>
+<span id="cb2-786"><a href="#cb2-786" tabindex="-1"></a><span class="co">#> ID Choice_situation Block alt1_x1 alt2_x1 alt1_x2 alt2_x2 alt1_x3 alt2_x3 group V_1 V_2 e_1 e_2 U_1 U_2</span></span>
+<span id="cb2-787"><a href="#cb2-787" tabindex="-1"></a><span class="co">#> 1 1 1 1 80 20 2.5 20.0 10 5 1 -0.775 -1.500 -1.1552146 1.6918663 -1.930215 0.1918663</span></span>
+<span id="cb2-788"><a href="#cb2-788" tabindex="-1"></a><span class="co">#> 2 1 2 1 60 40 5.0 10.0 5 10 1 -0.850 -0.900 3.5255143 2.5874719 2.675514 1.6874719</span></span>
+<span id="cb2-789"><a href="#cb2-789" tabindex="-1"></a><span class="co">#> 3 1 3 1 60 20 20.0 20.0 0 10 1 -2.000 -1.400 -0.1288440 3.2280170 -2.128844 1.8280170</span></span>
+<span id="cb2-790"><a href="#cb2-790" tabindex="-1"></a><span class="co">#> 4 1 4 1 20 80 20.0 2.5 0 10 1 -1.600 -0.775 -0.3072974 -0.3710956 -1.907297 -1.1460956</span></span>
+<span id="cb2-791"><a href="#cb2-791" tabindex="-1"></a><span class="co">#> 5 1 5 1 40 80 10.0 5.0 10 5 1 -0.900 -1.050 -0.6042191 -0.1952303 -1.504219 -1.2452303</span></span>
+<span id="cb2-792"><a href="#cb2-792" tabindex="-1"></a><span class="co">#> 6 1 6 1 60 80 5.0 2.5 0 0 1 -0.950 -0.975 -0.6233011 -0.2803958 -1.573301 -1.2553958</span></span>
+<span id="cb2-793"><a href="#cb2-793" tabindex="-1"></a><span class="co">#> CHOICE</span></span>
+<span id="cb2-794"><a href="#cb2-794" tabindex="-1"></a><span class="co">#> 1 2</span></span>
+<span id="cb2-795"><a href="#cb2-795" tabindex="-1"></a><span class="co">#> 2 1</span></span>
+<span id="cb2-796"><a href="#cb2-796" tabindex="-1"></a><span class="co">#> 3 2</span></span>
+<span id="cb2-797"><a href="#cb2-797" tabindex="-1"></a><span class="co">#> 4 2</span></span>
+<span id="cb2-798"><a href="#cb2-798" tabindex="-1"></a><span class="co">#> 5 2</span></span>
+<span id="cb2-799"><a href="#cb2-799" tabindex="-1"></a><span class="co">#> 6 2</span></span>
+<span id="cb2-800"><a href="#cb2-800" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-801"><a href="#cb2-801" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-802"><a href="#cb2-802" tabindex="-1"></a><span class="co">#> This is the utility functions </span></span>
+<span id="cb2-803"><a href="#cb2-803" tabindex="-1"></a><span class="co">#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319 </span></span>
+<span id="cb2-804"><a href="#cb2-804" tabindex="-1"></a><span class="co">#> Initial gradient value:</span></span>
+<span id="cb2-805"><a href="#cb2-805" tabindex="-1"></a><span class="co">#> bpreis blade bwarte </span></span>
+<span id="cb2-806"><a href="#cb2-806" tabindex="-1"></a><span class="co">#> -1060.0 -832.5 460.0 </span></span>
+<span id="cb2-807"><a href="#cb2-807" tabindex="-1"></a><span class="co">#> initial value 998.131940 </span></span>
+<span id="cb2-808"><a href="#cb2-808" tabindex="-1"></a><span class="co">#> iter 2 value 994.307556</span></span>
+<span id="cb2-809"><a href="#cb2-809" tabindex="-1"></a><span class="co">#> iter 3 value 972.255010</span></span>
+<span id="cb2-810"><a href="#cb2-810" tabindex="-1"></a><span class="co">#> iter 4 value 972.242499</span></span>
+<span id="cb2-811"><a href="#cb2-811" tabindex="-1"></a><span class="co">#> iter 5 value 968.104609</span></span>
+<span id="cb2-812"><a href="#cb2-812" tabindex="-1"></a><span class="co">#> iter 6 value 968.103010</span></span>
+<span id="cb2-813"><a href="#cb2-813" tabindex="-1"></a><span class="co">#> iter 6 value 968.103008</span></span>
+<span id="cb2-814"><a href="#cb2-814" tabindex="-1"></a><span class="co">#> iter 6 value 968.103008</span></span>
+<span id="cb2-815"><a href="#cb2-815" tabindex="-1"></a><span class="co">#> final value 968.103008 </span></span>
+<span id="cb2-816"><a href="#cb2-816" tabindex="-1"></a><span class="co">#> converged</span></span>
+<span id="cb2-817"><a href="#cb2-817" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-818"><a href="#cb2-818" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-819"><a href="#cb2-819" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-820"><a href="#cb2-820" tabindex="-1"></a><span class="co">#> \ vars n mean sd min max range se</span></span>
+<span id="cb2-821"><a href="#cb2-821" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-822"><a href="#cb2-822" tabindex="-1"></a><span class="co">#> est_bpreis 1 2 -0.01 0.00 -0.01 -0.01 0.00 0.00</span></span>
+<span id="cb2-823"><a href="#cb2-823" tabindex="-1"></a><span class="co">#> est_blade 2 2 -0.05 0.00 -0.05 -0.05 0.00 0.00</span></span>
+<span id="cb2-824"><a href="#cb2-824" tabindex="-1"></a><span class="co">#> est_bwarte 3 2 0.02 0.00 0.01 0.02 0.00 0.00</span></span>
+<span id="cb2-825"><a href="#cb2-825" tabindex="-1"></a><span class="co">#> rob_pval0_bpreis 4 2 0.00 0.00 0.00 0.00 0.00 0.00</span></span>
+<span id="cb2-826"><a href="#cb2-826" tabindex="-1"></a><span class="co">#> rob_pval0_blade 5 2 0.00 0.00 0.00 0.00 0.00 0.00</span></span>
+<span id="cb2-827"><a href="#cb2-827" tabindex="-1"></a><span class="co">#> rob_pval0_bwarte 6 2 0.12 0.08 0.06 0.18 0.12 0.06</span></span>
+<span id="cb2-828"><a href="#cb2-828" tabindex="-1"></a><span class="co">#> ================ ==== === ===== ==== ===== ===== ===== ====</span></span>
+<span id="cb2-829"><a href="#cb2-829" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-830"><a href="#cb2-830" tabindex="-1"></a><span class="co">#> FALSE </span></span>
+<span id="cb2-831"><a href="#cb2-831" tabindex="-1"></a><span class="co">#> 100 </span></span>
+<span id="cb2-832"><a href="#cb2-832" tabindex="-1"></a><span class="co">#> 9.804 sec elapsed</span></span>
+<span id="cb2-833"><a href="#cb2-833" tabindex="-1"></a><span class="co">#> $tic</span></span>
+<span id="cb2-834"><a href="#cb2-834" tabindex="-1"></a><span class="co">#> elapsed </span></span>
+<span id="cb2-835"><a href="#cb2-835" tabindex="-1"></a><span class="co">#> 10314.36 </span></span>
+<span id="cb2-836"><a href="#cb2-836" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-837"><a href="#cb2-837" tabindex="-1"></a><span class="co">#> $toc</span></span>
+<span id="cb2-838"><a href="#cb2-838" tabindex="-1"></a><span class="co">#> elapsed </span></span>
+<span id="cb2-839"><a href="#cb2-839" tabindex="-1"></a><span class="co">#> 10324.16 </span></span>
+<span id="cb2-840"><a href="#cb2-840" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-841"><a href="#cb2-841" tabindex="-1"></a><span class="co">#> $msg</span></span>
+<span id="cb2-842"><a href="#cb2-842" tabindex="-1"></a><span class="co">#> logical(0)</span></span>
+<span id="cb2-843"><a href="#cb2-843" tabindex="-1"></a><span class="co">#> </span></span>
+<span id="cb2-844"><a href="#cb2-844" tabindex="-1"></a><span class="co">#> $callback_msg</span></span>
+<span id="cb2-845"><a href="#cb2-845" tabindex="-1"></a><span class="co">#> [1] "9.804 sec elapsed"</span></span></code></pre></div>
+<p><img src="data:image/png;base64,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" width="100%" /><img src="data:image/png;base64,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" width="100%" /><img src="data:image/png;base64,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" width="100%" /></p>
+
+</body>
+</html>
diff --git a/README.md b/README.md
index 77d6112d23362c6ce53d493c022d351aaba0354b..cb74f733011f11cf3f7931213d4af0e83b587173 100644
--- a/README.md
+++ b/README.md
@@ -10,7 +10,7 @@ The goal of simulateDCE is to make it easy to simulate choice experiment
datasets using designs from NGENE or `spdesign`. You have to store the
design file in a subfolder and need to specify certain parameters and
the utility functions for the data generating process. The package is
-useful for
+useful for:
1. Test different designs in terms of statistical power, efficiency and
unbiasedness
@@ -36,6 +36,7 @@ need to install the `remotes` package first. The current version is
alpha and there is no version on cran:
``` r
+
install.packages("remotes")
remotes::install_gitlab(repo = "dj44vuri/simulateDCE" , host = "https://git.idiv.de")
```
@@ -46,15 +47,11 @@ This is a basic example for a simulation:
``` r
+
rm(list=ls())
library(simulateDCE)
library(rlang)
library(formula.tools)
-#>
-#> Attaching package: 'formula.tools'
-#> The following object is masked from 'package:rlang':
-#>
-#> env
library(rlang)
@@ -69,19 +66,21 @@ nosim= 2 # number of simulations to run (about 500 is minimum)
-# bpreis = -0.036
-# blade = -0.034
-# bwarte = -0.049
+# bcoeff <- list(
+# bpreis = -0.036,
+# blade = -0.034,
+# bwarte = -0.049)
decisiongroups=c(0,0.7,1)
# wrong parameters
-#
-bpreis = -0.01
-blade = -0.07
-bwarte = 0.02
+# place b coefficients into an r list:
+bcoeff = list(
+ bpreis = -0.01,
+ blade = -0.07,
+ bwarte = 0.02)
manipulations = list(alt1.x2= expr(alt1.x2/10),
alt1.x3= expr(alt1.x3/10),
@@ -108,7 +107,7 @@ ul<-list( u1 =
destype="ngene"
sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
- designpath = designpath, u=ul)
+ designpath = designpath, u=ul, bcoeff = bcoeff)
#> Utility function used in simulation, ie the true utility:
#>
#> $u1
@@ -145,20 +144,20 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block
-#> 1 1 7 80 2.5 10.0 60 20.0 10 1
-#> 2 1 19 20 2.5 5.0 60 2.5 0 1
-#> 3 1 30 20 10.0 5.0 80 5.0 10 1
-#> 4 1 32 40 20.0 2.5 80 2.5 0 1
-#> 5 1 39 40 20.0 0.0 80 10.0 10 1
-#> 6 1 48 60 5.0 2.5 20 5.0 10 1
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -0.775 -1.800 -0.28937157 2.15097352 -1.064372 0.3509735 2
-#> 2 1 -0.275 -0.775 -0.96139278 -0.20476786 -1.236393 -0.9797679 2
-#> 3 1 -0.800 -0.950 -1.22764761 -0.06043672 -2.027648 -1.0104367 2
-#> 4 1 -1.750 -0.975 -0.01653508 0.83311025 -1.766535 -0.1418897 2
-#> 5 1 -1.800 -1.300 0.55064443 -0.20286674 -1.249356 -1.5028667 1
-#> 6 1 -0.900 -0.350 -0.31623091 0.72473769 -1.216231 0.3747377 2
+#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2
+#> 1 1 7 80 2.5 10.0 60 20.0 10 1 1 -0.775 -1.800 -0.15343271 3.6612318 -0.9284327 1.8612318
+#> 2 1 19 20 2.5 5.0 60 2.5 0 1 1 -0.275 -0.775 0.47936686 -0.8086989 0.2043669 -1.5836989
+#> 3 1 30 20 10.0 5.0 80 5.0 10 1 1 -0.800 -0.950 0.12634298 1.2300690 -0.6736570 0.2800690
+#> 4 1 32 40 20.0 2.5 80 2.5 0 1 1 -1.750 -0.975 2.08710825 -0.1882935 0.3371082 -1.1632935
+#> 5 1 39 40 20.0 0.0 80 10.0 10 1 1 -1.800 -1.300 1.05540385 3.1339326 -0.7445961 1.8339326
+#> 6 1 48 60 5.0 2.5 20 5.0 10 1 1 -0.900 -0.350 0.07255885 -0.1156742 -0.8274412 -0.4656742
+#> CHOICE
+#> 1 2
+#> 2 1
+#> 3 2
+#> 4 1
+#> 5 2
+#> 6 2
#>
#>
#> This is Run number 1
@@ -173,36 +172,36 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block
-#> 1 1 7 80 2.5 10.0 60 20.0 10 1
-#> 2 1 19 20 2.5 5.0 60 2.5 0 1
-#> 3 1 30 20 10.0 5.0 80 5.0 10 1
-#> 4 1 32 40 20.0 2.5 80 2.5 0 1
-#> 5 1 39 40 20.0 0.0 80 10.0 10 1
-#> 6 1 48 60 5.0 2.5 20 5.0 10 1
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -0.775 -1.800 0.4008023 4.3514331 -0.3741977 2.5514331 2
-#> 2 1 -0.275 -0.775 -0.1892883 -0.7606078 -0.4642883 -1.5356078 1
-#> 3 1 -0.800 -0.950 1.2266380 -0.2061132 0.4266380 -1.1561132 1
-#> 4 1 -1.750 -0.975 1.5461599 -0.9432939 -0.2038401 -1.9182939 1
-#> 5 1 -1.800 -1.300 -0.9309889 1.7478688 -2.7309889 0.4478688 2
-#> 6 1 -0.900 -0.350 1.3557092 1.1181441 0.4557092 0.7681441 2
+#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2
+#> 1 1 7 80 2.5 10.0 60 20.0 10 1 1 -0.775 -1.800 -1.2775839 1.5689946 -2.052584 -0.2310054
+#> 2 1 19 20 2.5 5.0 60 2.5 0 1 1 -0.275 -0.775 0.5934850 0.5453996 0.318485 -0.2296004
+#> 3 1 30 20 10.0 5.0 80 5.0 10 1 1 -0.800 -0.950 -0.5127855 1.7551185 -1.312785 0.8051185
+#> 4 1 32 40 20.0 2.5 80 2.5 0 1 1 -1.750 -0.975 3.4643234 1.3685812 1.714323 0.3935812
+#> 5 1 39 40 20.0 0.0 80 10.0 10 1 1 -1.800 -1.300 -0.5128262 0.3011019 -2.312826 -0.9988981
+#> 6 1 48 60 5.0 2.5 20 5.0 10 1 1 -0.900 -0.350 4.3343477 1.2265189 3.434348 0.8765189
+#> CHOICE
+#> 1 2
+#> 2 1
+#> 3 2
+#> 4 1
+#> 5 2
+#> 6 1
#>
#>
#> This is the utility functions
#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319
#> Initial gradient value:
-#> bpreis blade bwarte
-#> 140 -1110 320
+#> bpreis blade bwarte
+#> -1060.0 -812.5 520.0
#> initial value 998.131940
-#> iter 2 value 987.542841
-#> iter 3 value 976.359534
-#> iter 4 value 976.315710
-#> iter 5 value 971.176423
-#> iter 6 value 971.173751
-#> iter 6 value 971.173748
-#> iter 6 value 971.173748
-#> final value 971.173748
+#> iter 2 value 994.260781
+#> iter 3 value 974.092906
+#> iter 4 value 973.856287
+#> iter 5 value 970.270450
+#> iter 6 value 970.262794
+#> iter 6 value 970.262788
+#> iter 6 value 970.262788
+#> final value 970.262788
#> converged
#> This is Run number 2
#> does sou_gis exist: FALSE
@@ -216,52 +215,52 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block
-#> 1 1 7 80 2.5 10.0 60 20.0 10 1
-#> 2 1 19 20 2.5 5.0 60 2.5 0 1
-#> 3 1 30 20 10.0 5.0 80 5.0 10 1
-#> 4 1 32 40 20.0 2.5 80 2.5 0 1
-#> 5 1 39 40 20.0 0.0 80 10.0 10 1
-#> 6 1 48 60 5.0 2.5 20 5.0 10 1
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -0.775 -1.800 0.93025769 2.47570731 0.1552577 0.6757073 2
-#> 2 1 -0.275 -0.775 1.60707885 -0.35547058 1.3320789 -1.1304706 1
-#> 3 1 -0.800 -0.950 1.27471866 -0.07559595 0.4747187 -1.0255960 1
-#> 4 1 -1.750 -0.975 0.39775368 -0.33144802 -1.3522463 -1.3064480 2
-#> 5 1 -1.800 -1.300 1.28873901 1.16104216 -0.5112610 -0.1389578 2
-#> 6 1 -0.900 -0.350 0.05237432 0.77241297 -0.8476257 0.4224130 2
+#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2
+#> 1 1 7 80 2.5 10.0 60 20.0 10 1 1 -0.775 -1.800 0.34553136 -0.8375727 -0.4294686 -2.6375727
+#> 2 1 19 20 2.5 5.0 60 2.5 0 1 1 -0.275 -0.775 -1.32361481 0.3195766 -1.5986148 -0.4554234
+#> 3 1 30 20 10.0 5.0 80 5.0 10 1 1 -0.800 -0.950 0.08515524 -0.6090259 -0.7148448 -1.5590259
+#> 4 1 32 40 20.0 2.5 80 2.5 0 1 1 -1.750 -0.975 -0.18021132 2.3073397 -1.9302113 1.3323397
+#> 5 1 39 40 20.0 0.0 80 10.0 10 1 1 -1.800 -1.300 -0.55591900 3.4630292 -2.3559190 2.1630292
+#> 6 1 48 60 5.0 2.5 20 5.0 10 1 1 -0.900 -0.350 -0.29734711 3.0420404 -1.1973471 2.6920404
+#> CHOICE
+#> 1 1
+#> 2 2
+#> 3 1
+#> 4 2
+#> 5 2
+#> 6 2
#>
#>
#> This is the utility functions
#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319
#> Initial gradient value:
-#> bpreis blade bwarte
-#> -520 -925 320
+#> bpreis blade bwarte
+#> 440.0 -1087.5 447.5
#> initial value 998.131940
-#> iter 2 value 989.267873
-#> iter 3 value 979.462597
-#> iter 4 value 979.399625
-#> iter 5 value 974.067680
-#> iter 6 value 974.065735
-#> iter 6 value 974.065733
-#> iter 6 value 974.065733
-#> final value 974.065733
+#> iter 2 value 995.094499
+#> iter 3 value 974.488144
+#> iter 4 value 974.227531
+#> iter 5 value 971.482008
+#> iter 6 value 971.477251
+#> iter 6 value 971.477249
+#> iter 6 value 971.477249
+#> final value 971.477249
#> converged
#>
#>
#> ================ ==== === ===== ==== ===== ===== ===== ====
#> \ vars n mean sd min max range se
#> ================ ==== === ===== ==== ===== ===== ===== ====
-#> est_bpreis 1 2 -0.01 0.00 -0.01 -0.01 0.00 0.00
-#> est_blade 2 2 -0.05 0.00 -0.05 -0.04 0.00 0.00
-#> est_bwarte 3 2 0.01 0.00 0.01 0.01 0.00 0.00
-#> rob_pval0_bpreis 4 2 0.00 0.00 0.00 0.00 0.00 0.00
+#> est_bpreis 1 2 -0.01 0.00 -0.01 0.00 0.00 0.00
+#> est_blade 2 2 -0.04 0.00 -0.04 -0.04 0.00 0.00
+#> est_bwarte 3 2 0.03 0.00 0.03 0.03 0.00 0.00
+#> rob_pval0_bpreis 4 2 0.01 0.01 0.00 0.02 0.02 0.01
#> rob_pval0_blade 5 2 0.00 0.00 0.00 0.00 0.00 0.00
-#> rob_pval0_bwarte 6 2 0.34 0.02 0.33 0.36 0.03 0.01
+#> rob_pval0_bwarte 6 2 0.01 0.00 0.01 0.01 0.00 0.00
#> ================ ==== === ===== ==== ===== ===== ===== ====
#>
-#> FALSE
-#> 100
+#> TRUE
+#> 100
#> Utility function used in simulation, ie the true utility:
#>
#> $u1
@@ -298,20 +297,20 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block
-#> 1 1 12 60 2.5 0.0 20 20.0 10 1
-#> 2 1 16 20 10.0 5.0 40 5.0 0 1
-#> 3 1 17 20 20.0 0.0 80 10.0 10 1
-#> 4 1 25 60 5.0 10.0 20 20.0 5 1
-#> 5 1 29 20 5.0 10.0 80 5.0 0 1
-#> 6 1 32 40 10.0 2.5 80 2.5 5 1
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -0.775 -1.400 0.5000790 -1.2708067 -0.2749210 -2.6708067 1
-#> 2 1 -0.800 -0.750 -1.9947176 -0.6174753 -2.7947176 -1.3674753 2
-#> 3 1 -1.600 -1.300 0.6003003 1.1010281 -0.9996997 -0.1989719 2
-#> 4 1 -0.750 -1.500 -1.2502306 2.4331480 -2.0002306 0.9331480 2
-#> 5 1 -0.350 -1.150 0.1058614 1.8360816 -0.2441386 0.6860816 2
-#> 6 1 -1.050 -0.875 1.8917336 0.7028783 0.8417336 -0.1721217 1
+#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2
+#> 1 1 12 60 2.5 0.0 20 20.0 10 1 1 -0.775 -1.400 0.63130736 -1.4347994 -0.1436926 -2.8347994
+#> 2 1 16 20 10.0 5.0 40 5.0 0 1 1 -0.800 -0.750 5.09739937 0.4118885 4.2973994 -0.3381115
+#> 3 1 17 20 20.0 0.0 80 10.0 10 1 1 -1.600 -1.300 0.22397799 0.4666321 -1.3760220 -0.8333679
+#> 4 1 25 60 5.0 10.0 20 20.0 5 1 1 -0.750 -1.500 -0.05146482 2.2007592 -0.8014648 0.7007592
+#> 5 1 29 20 5.0 10.0 80 5.0 0 1 1 -0.350 -1.150 1.57620781 4.9154679 1.2262078 3.7654679
+#> 6 1 32 40 10.0 2.5 80 2.5 5 1 1 -1.050 -0.875 -0.47930823 0.7058788 -1.5293082 -0.1691212
+#> CHOICE
+#> 1 1
+#> 2 1
+#> 3 2
+#> 4 2
+#> 5 2
+#> 6 2
#>
#>
#> This is Run number 1
@@ -326,36 +325,37 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block
-#> 1 1 12 60 2.5 0.0 20 20.0 10 1
-#> 2 1 16 20 10.0 5.0 40 5.0 0 1
-#> 3 1 17 20 20.0 0.0 80 10.0 10 1
-#> 4 1 25 60 5.0 10.0 20 20.0 5 1
-#> 5 1 29 20 5.0 10.0 80 5.0 0 1
-#> 6 1 32 40 10.0 2.5 80 2.5 5 1
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -0.775 -1.400 2.6464470 1.8930848 1.8714470 0.4930848 1
-#> 2 1 -0.800 -0.750 0.6943881 -0.0951414 -0.1056119 -0.8451414 1
-#> 3 1 -1.600 -1.300 3.0441699 2.6667389 1.4441699 1.3667389 1
-#> 4 1 -0.750 -1.500 1.1984493 1.9151346 0.4484493 0.4151346 1
-#> 5 1 -0.350 -1.150 3.5252196 -0.8557313 3.1752196 -2.0057313 1
-#> 6 1 -1.050 -0.875 0.5099513 -0.4707311 -0.5400487 -1.3457311 1
+#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2
+#> 1 1 12 60 2.5 0.0 20 20.0 10 1 1 -0.775 -1.400 0.3494617 0.1551114 -0.42553827 -1.24488857
+#> 2 1 16 20 10.0 5.0 40 5.0 0 1 1 -0.800 -0.750 1.5845207 0.5556039 0.78452066 -0.19439613
+#> 3 1 17 20 20.0 0.0 80 10.0 10 1 1 -1.600 -1.300 4.1993459 -0.1612424 2.59934589 -1.46124241
+#> 4 1 25 60 5.0 10.0 20 20.0 5 1 1 -0.750 -1.500 0.6527215 1.3949219 -0.09727852 -0.10507806
+#> 5 1 29 20 5.0 10.0 80 5.0 0 1 1 -0.350 -1.150 2.6927356 -1.3232777 2.34273564 -2.47327770
+#> 6 1 32 40 10.0 2.5 80 2.5 5 1 1 -1.050 -0.875 0.3758168 0.8556930 -0.67418318 -0.01930696
+#> CHOICE
+#> 1 1
+#> 2 1
+#> 3 1
+#> 4 1
+#> 5 1
+#> 6 2
#>
#>
#> This is the utility functions
#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319
#> Initial gradient value:
#> bpreis blade bwarte
-#> -1440.0 -1057.5 510.0
+#> -2340.0 -857.5 510.0
#> initial value 998.131940
-#> iter 2 value 992.072549
-#> iter 3 value 964.484472
-#> iter 4 value 964.438157
-#> iter 5 value 960.231915
-#> iter 6 value 960.220989
-#> iter 6 value 960.220975
-#> iter 6 value 960.220975
-#> final value 960.220975
+#> iter 2 value 989.566757
+#> iter 3 value 968.906950
+#> iter 4 value 968.775516
+#> iter 5 value 959.377427
+#> iter 6 value 959.364632
+#> iter 7 value 959.364588
+#> iter 7 value 959.364588
+#> iter 7 value 959.364588
+#> final value 959.364588
#> converged
#> This is Run number 2
#> does sou_gis exist: FALSE
@@ -369,37 +369,37 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block
-#> 1 1 12 60 2.5 0.0 20 20.0 10 1
-#> 2 1 16 20 10.0 5.0 40 5.0 0 1
-#> 3 1 17 20 20.0 0.0 80 10.0 10 1
-#> 4 1 25 60 5.0 10.0 20 20.0 5 1
-#> 5 1 29 20 5.0 10.0 80 5.0 0 1
-#> 6 1 32 40 10.0 2.5 80 2.5 5 1
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -0.775 -1.400 -0.8673571 0.5735753 -1.6423571 -0.8264247 2
-#> 2 1 -0.800 -0.750 0.1338568 2.1243864 -0.6661432 1.3743864 2
-#> 3 1 -1.600 -1.300 1.3074577 -0.1769248 -0.2925423 -1.4769248 1
-#> 4 1 -0.750 -1.500 1.7452195 -0.7334989 0.9952195 -2.2334989 1
-#> 5 1 -0.350 -1.150 3.2417667 0.8099365 2.8917667 -0.3400635 1
-#> 6 1 -1.050 -0.875 -0.8125169 -0.6517018 -1.8625169 -1.5267018 2
+#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1
+#> 1 1 12 60 2.5 0.0 20 20.0 10 1 1 -0.775 -1.400 -0.5067469 -4.908678e-05 -1.2817469
+#> 2 1 16 20 10.0 5.0 40 5.0 0 1 1 -0.800 -0.750 2.1209149 5.835693e-01 1.3209149
+#> 3 1 17 20 20.0 0.0 80 10.0 10 1 1 -1.600 -1.300 -0.3310010 7.106139e-01 -1.9310010
+#> 4 1 25 60 5.0 10.0 20 20.0 5 1 1 -0.750 -1.500 1.0469501 3.053872e-01 0.2969501
+#> 5 1 29 20 5.0 10.0 80 5.0 0 1 1 -0.350 -1.150 1.2182730 -6.215119e-01 0.8682730
+#> 6 1 32 40 10.0 2.5 80 2.5 5 1 1 -1.050 -0.875 -0.3318808 5.251218e+00 -1.3818808
+#> U_2 CHOICE
+#> 1 -1.4000491 1
+#> 2 -0.1664307 1
+#> 3 -0.5893861 2
+#> 4 -1.1946128 1
+#> 5 -1.7715119 1
+#> 6 4.3762180 2
#>
#>
#> This is the utility functions
#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319
#> Initial gradient value:
#> bpreis blade bwarte
-#> -640.0 -1295.0 362.5
+#> -2120.0 -842.5 582.5
#> initial value 998.131940
-#> iter 2 value 981.273463
-#> iter 3 value 964.055548
-#> iter 4 value 963.472083
-#> iter 5 value 957.462611
-#> iter 6 value 957.449595
-#> iter 7 value 957.449577
-#> iter 7 value 957.449577
-#> iter 7 value 957.449577
-#> final value 957.449577
+#> iter 2 value 990.498814
+#> iter 3 value 970.036278
+#> iter 4 value 970.031934
+#> iter 5 value 961.943463
+#> iter 6 value 961.698866
+#> iter 7 value 961.698562
+#> iter 7 value 961.698561
+#> iter 7 value 961.698561
+#> final value 961.698561
#> converged
#>
#>
@@ -407,15 +407,15 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> \ vars n mean sd min max range se
#> ================ ==== === ===== ==== ===== ===== ===== ====
#> est_bpreis 1 2 -0.01 0.00 -0.01 -0.01 0.00 0.00
-#> est_blade 2 2 -0.05 0.00 -0.06 -0.05 0.01 0.00
-#> est_bwarte 3 2 0.01 0.01 0.00 0.01 0.01 0.01
+#> est_blade 2 2 -0.05 0.00 -0.05 -0.05 0.00 0.00
+#> est_bwarte 3 2 0.02 0.01 0.01 0.02 0.01 0.00
#> rob_pval0_bpreis 4 2 0.00 0.00 0.00 0.00 0.00 0.00
#> rob_pval0_blade 5 2 0.00 0.00 0.00 0.00 0.00 0.00
-#> rob_pval0_bwarte 6 2 0.53 0.52 0.16 0.90 0.74 0.37
+#> rob_pval0_bwarte 6 2 0.16 0.19 0.03 0.30 0.27 0.13
#> ================ ==== === ===== ==== ===== ===== ===== ====
#>
-#> FALSE
-#> 100
+#> FALSE TRUE
+#> 50 50
#> Utility function used in simulation, ie the true utility:
#>
#> $u1
@@ -452,20 +452,20 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block
-#> 1 1 3 80 5.0 0.0 20 5.0 10.0 1
-#> 2 1 5 60 2.5 5.0 20 20.0 5.0 1
-#> 3 1 10 80 2.5 2.5 20 20.0 0.0 1
-#> 4 1 34 80 2.5 5.0 60 5.0 5.0 1
-#> 5 1 37 40 5.0 10.0 60 5.0 2.5 1
-#> 6 1 39 20 20.0 2.5 60 2.5 2.5 1
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -1.150 -0.350 1.018356215 -0.622267218 -0.13164379 -0.9722672 1
-#> 2 1 -0.675 -1.500 2.065375543 0.448415040 1.39037554 -1.0515850 1
-#> 3 1 -0.925 -1.600 0.068572712 0.001884789 -0.85642729 -1.5981152 1
-#> 4 1 -0.875 -0.850 4.451064209 -0.131594375 3.57606421 -0.9815944 1
-#> 5 1 -0.550 -0.900 0.001325549 1.769899979 -0.54867445 0.8699000 2
-#> 6 1 -1.550 -0.725 1.585052229 -0.559602808 0.03505223 -1.2846028 1
+#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1
+#> 1 1 3 80 5.0 0.0 20 5.0 10.0 1 1 -1.150 -0.350 1.88045081 0.33059180 0.7304508
+#> 2 1 5 60 2.5 5.0 20 20.0 5.0 1 1 -0.675 -1.500 -0.08733163 -0.07195918 -0.7623316
+#> 3 1 10 80 2.5 2.5 20 20.0 0.0 1 1 -0.925 -1.600 -0.31269859 3.95512677 -1.2376986
+#> 4 1 34 80 2.5 5.0 60 5.0 5.0 1 1 -0.875 -0.850 0.20206751 -0.87018279 -0.6729325
+#> 5 1 37 40 5.0 10.0 60 5.0 2.5 1 1 -0.550 -0.900 -0.25607132 -1.21928402 -0.8060713
+#> 6 1 39 20 20.0 2.5 60 2.5 2.5 1 1 -1.550 -0.725 1.39833272 -0.08165078 -0.1516673
+#> U_2 CHOICE
+#> 1 -0.0194082 1
+#> 2 -1.5719592 1
+#> 3 2.3551268 2
+#> 4 -1.7201828 1
+#> 5 -2.1192840 1
+#> 6 -0.8066508 1
#>
#>
#> This is Run number 1
@@ -480,36 +480,37 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block
-#> 1 1 3 80 5.0 0.0 20 5.0 10.0 1
-#> 2 1 5 60 2.5 5.0 20 20.0 5.0 1
-#> 3 1 10 80 2.5 2.5 20 20.0 0.0 1
-#> 4 1 34 80 2.5 5.0 60 5.0 5.0 1
-#> 5 1 37 40 5.0 10.0 60 5.0 2.5 1
-#> 6 1 39 20 20.0 2.5 60 2.5 2.5 1
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -1.150 -0.350 -0.08786308 -0.5863325 -1.23786308 -0.9363325 2
-#> 2 1 -0.675 -1.500 0.06248520 1.0111311 -0.61251480 -0.4888689 2
-#> 3 1 -0.925 -1.600 0.95443352 -0.3946771 0.02943352 -1.9946771 1
-#> 4 1 -0.875 -0.850 -0.76545318 1.6682085 -1.64045318 0.8182085 2
-#> 5 1 -0.550 -0.900 1.13173817 -0.3986287 0.58173817 -1.2986287 1
-#> 6 1 -1.550 -0.725 3.42387572 1.2824413 1.87387572 0.5574413 1
+#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1
+#> 1 1 3 80 5.0 0.0 20 5.0 10.0 1 1 -1.150 -0.350 -0.0940785 -0.8728874 -1.24407850
+#> 2 1 5 60 2.5 5.0 20 20.0 5.0 1 1 -0.675 -1.500 -0.6796651 -1.1297414 -1.35466507
+#> 3 1 10 80 2.5 2.5 20 20.0 0.0 1 1 -0.925 -1.600 1.7899847 0.6372528 0.86498471
+#> 4 1 34 80 2.5 5.0 60 5.0 5.0 1 1 -0.875 -0.850 0.9429192 0.7744473 0.06791921
+#> 5 1 37 40 5.0 10.0 60 5.0 2.5 1 1 -0.550 -0.900 0.1003092 2.5583115 -0.44969083
+#> 6 1 39 20 20.0 2.5 60 2.5 2.5 1 1 -1.550 -0.725 -0.3851894 0.9776369 -1.93518939
+#> U_2 CHOICE
+#> 1 -1.22288745 2
+#> 2 -2.62974141 1
+#> 3 -0.96274717 1
+#> 4 -0.07555271 1
+#> 5 1.65831145 2
+#> 6 0.25263691 2
#>
#>
#> This is the utility functions
#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319
#> Initial gradient value:
#> bpreis blade bwarte
-#> -960.0 -1017.5 245.0
+#> -2300.0 -967.5 417.5
#> initial value 998.131940
-#> iter 2 value 994.181427
-#> iter 3 value 972.722564
-#> iter 4 value 971.807620
-#> iter 5 value 969.894601
-#> iter 6 value 969.892112
-#> iter 6 value 969.892111
-#> iter 6 value 969.892111
-#> final value 969.892111
+#> iter 2 value 989.783897
+#> iter 3 value 967.441065
+#> iter 4 value 966.807343
+#> iter 5 value 957.535574
+#> iter 6 value 957.518843
+#> iter 7 value 957.518805
+#> iter 7 value 957.518805
+#> iter 7 value 957.518805
+#> final value 957.518805
#> converged
#> This is Run number 2
#> does sou_gis exist: FALSE
@@ -523,37 +524,36 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block
-#> 1 1 3 80 5.0 0.0 20 5.0 10.0 1
-#> 2 1 5 60 2.5 5.0 20 20.0 5.0 1
-#> 3 1 10 80 2.5 2.5 20 20.0 0.0 1
-#> 4 1 34 80 2.5 5.0 60 5.0 5.0 1
-#> 5 1 37 40 5.0 10.0 60 5.0 2.5 1
-#> 6 1 39 20 20.0 2.5 60 2.5 2.5 1
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -1.150 -0.350 0.6747222 0.25151850 -0.4752778 -0.0984815 2
-#> 2 1 -0.675 -1.500 1.8163839 -0.09688587 1.1413839 -1.5968859 1
-#> 3 1 -0.925 -1.600 -0.8974158 3.69592175 -1.8224158 2.0959217 2
-#> 4 1 -0.875 -0.850 -0.5523539 3.18018561 -1.4273539 2.3301856 2
-#> 5 1 -0.550 -0.900 -1.0057814 0.20974090 -1.5557814 -0.6902591 2
-#> 6 1 -1.550 -0.725 0.9409876 0.52310305 -0.6090124 -0.2018970 2
+#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1
+#> 1 1 3 80 5.0 0.0 20 5.0 10.0 1 1 -1.150 -0.350 0.39615659 0.74248610 -0.7538434
+#> 2 1 5 60 2.5 5.0 20 20.0 5.0 1 1 -0.675 -1.500 -0.17578286 0.04260786 -0.8507829
+#> 3 1 10 80 2.5 2.5 20 20.0 0.0 1 1 -0.925 -1.600 0.44905385 0.79514566 -0.4759461
+#> 4 1 34 80 2.5 5.0 60 5.0 5.0 1 1 -0.875 -0.850 0.27140789 4.63953174 -0.6035921
+#> 5 1 37 40 5.0 10.0 60 5.0 2.5 1 1 -0.550 -0.900 -0.03370054 0.84622952 -0.5837005
+#> 6 1 39 20 20.0 2.5 60 2.5 2.5 1 1 -1.550 -0.725 -0.47233862 1.05805421 -2.0223386
+#> U_2 CHOICE
+#> 1 0.39248610 2
+#> 2 -1.45739214 1
+#> 3 -0.80485434 1
+#> 4 3.78953174 2
+#> 5 -0.05377048 2
+#> 6 0.33305421 2
#>
#>
#> This is the utility functions
#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319
#> Initial gradient value:
#> bpreis blade bwarte
-#> -2920.0 -597.5 467.5
+#> -1600.0 -857.5 402.5
#> initial value 998.131940
-#> iter 2 value 988.559582
-#> iter 3 value 984.350429
-#> iter 4 value 984.238420
-#> iter 5 value 967.198497
-#> iter 6 value 967.168244
-#> iter 7 value 967.168103
-#> iter 7 value 967.168103
-#> iter 7 value 967.168103
-#> final value 967.168103
+#> iter 2 value 993.094191
+#> iter 3 value 975.977284
+#> iter 4 value 975.860148
+#> iter 5 value 971.032264
+#> iter 6 value 971.027871
+#> iter 6 value 971.027867
+#> iter 6 value 971.027867
+#> final value 971.027867
#> converged
#>
#>
@@ -561,11 +561,11 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> \ vars n mean sd min max range se
#> ================ ==== === ===== ==== ===== ===== ===== ====
#> est_bpreis 1 2 -0.01 0.00 -0.01 -0.01 0.00 0.00
-#> est_blade 2 2 -0.04 0.01 -0.05 -0.04 0.01 0.00
-#> est_bwarte 3 2 0.00 0.01 -0.01 0.01 0.01 0.01
+#> est_blade 2 2 -0.05 0.01 -0.05 -0.04 0.01 0.01
+#> est_bwarte 3 2 0.00 0.01 0.00 0.01 0.01 0.00
#> rob_pval0_bpreis 4 2 0.00 0.00 0.00 0.00 0.00 0.00
#> rob_pval0_blade 5 2 0.00 0.00 0.00 0.00 0.00 0.00
-#> rob_pval0_bwarte 6 2 0.52 0.11 0.44 0.59 0.15 0.07
+#> rob_pval0_bwarte 6 2 0.68 0.20 0.54 0.82 0.28 0.14
#> ================ ==== === ===== ==== ===== ===== ===== ====
#>
#> FALSE
@@ -606,20 +606,20 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block
-#> 1 1 9 80 5.0 0 60 20.0 10.0 1
-#> 2 1 12 60 2.5 10 40 20.0 0.0 1
-#> 3 1 13 20 20.0 10 80 2.5 0.0 1
-#> 4 1 70 80 5.0 10 20 20.0 2.5 1
-#> 5 1 71 60 20.0 10 80 10.0 0.0 1
-#> 6 1 73 60 10.0 0 40 20.0 10.0 1
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -1.150 -1.800 0.458928485 2.0701754 -0.6910715 0.27017541 2
-#> 2 1 -0.575 -1.800 0.253655240 -0.6611997 -0.3213448 -2.46119970 1
-#> 3 1 -1.400 -0.975 -0.102031250 0.2036489 -1.5020312 -0.77135113 2
-#> 4 1 -0.950 -1.550 -0.559421410 0.8864091 -1.5094214 -0.66359093 2
-#> 5 1 -1.800 -1.500 5.674505169 1.5661040 3.8745052 0.06610405 1
-#> 6 1 -1.300 -1.600 -0.002309409 1.5711319 -1.3023094 -0.02886812 2
+#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2
+#> 1 1 9 80 5.0 0 60 20.0 10.0 1 1 -1.150 -1.800 0.8053210 -0.7760447 -0.34467900 -2.5760447
+#> 2 1 12 60 2.5 10 40 20.0 0.0 1 1 -0.575 -1.800 2.4581484 -0.5422855 1.88314842 -2.3422855
+#> 3 1 13 20 20.0 10 80 2.5 0.0 1 1 -1.400 -0.975 0.4806134 -1.7030310 -0.91938664 -2.6780310
+#> 4 1 70 80 5.0 10 20 20.0 2.5 1 1 -0.950 -1.550 -0.8558539 1.9784273 -1.80585392 0.4284273
+#> 5 1 71 60 20.0 10 80 10.0 0.0 1 1 -1.800 -1.500 1.4200481 0.8856199 -0.37995187 -0.6143801
+#> 6 1 73 60 10.0 0 40 20.0 10.0 1 1 -1.300 -1.600 1.3592506 -0.1823192 0.05925063 -1.7823192
+#> CHOICE
+#> 1 1
+#> 2 1
+#> 3 1
+#> 4 2
+#> 5 1
+#> 6 1
#>
#>
#> This is Run number 1
@@ -634,37 +634,37 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block
-#> 1 1 9 80 5.0 0 60 20.0 10.0 1
-#> 2 1 12 60 2.5 10 40 20.0 0.0 1
-#> 3 1 13 20 20.0 10 80 2.5 0.0 1
-#> 4 1 70 80 5.0 10 20 20.0 2.5 1
-#> 5 1 71 60 20.0 10 80 10.0 0.0 1
-#> 6 1 73 60 10.0 0 40 20.0 10.0 1
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -1.150 -1.800 -0.01463130 -0.22509832 -1.164631 -2.0250983 1
-#> 2 1 -0.575 -1.800 2.36022782 -0.36376052 1.785228 -2.1637605 1
-#> 3 1 -1.400 -0.975 1.59659499 -0.13121663 0.196595 -1.1062166 1
-#> 4 1 -0.950 -1.550 -1.33824416 1.40724463 -2.288244 -0.1427554 2
-#> 5 1 -1.800 -1.500 0.49308644 1.66211472 -1.306914 0.1621147 2
-#> 6 1 -1.300 -1.600 0.04407743 0.04227857 -1.255923 -1.5577214 1
+#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2
+#> 1 1 9 80 5.0 0 60 20.0 10.0 1 1 -1.150 -1.800 1.1057596 0.8176933 -0.04424039 -0.9823067
+#> 2 1 12 60 2.5 10 40 20.0 0.0 1 1 -0.575 -1.800 1.4664332 0.2855647 0.89143319 -1.5144353
+#> 3 1 13 20 20.0 10 80 2.5 0.0 1 1 -1.400 -0.975 -0.2567456 2.0307365 -1.65674558 1.0557365
+#> 4 1 70 80 5.0 10 20 20.0 2.5 1 1 -0.950 -1.550 1.7936733 0.2273817 0.84367334 -1.3226183
+#> 5 1 71 60 20.0 10 80 10.0 0.0 1 1 -1.800 -1.500 -0.5080847 1.8371868 -2.30808468 0.3371868
+#> 6 1 73 60 10.0 0 40 20.0 10.0 1 1 -1.300 -1.600 0.2315646 0.5250324 -1.06843538 -1.0749676
+#> CHOICE
+#> 1 1
+#> 2 1
+#> 3 2
+#> 4 1
+#> 5 2
+#> 6 1
#>
#>
#> This is the utility functions
#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319
#> Initial gradient value:
#> bpreis blade bwarte
-#> -2640.0 -3282.5 1152.5
+#> -2720.0 -3230.0 1477.5
#> initial value 998.131940
-#> iter 2 value 963.302525
-#> iter 3 value 925.984100
-#> iter 4 value 925.959587
-#> iter 5 value 905.721674
-#> iter 6 value 905.488066
-#> iter 7 value 905.484178
-#> iter 7 value 905.484176
-#> iter 7 value 905.484176
-#> final value 905.484176
+#> iter 2 value 961.903346
+#> iter 3 value 923.013503
+#> iter 4 value 921.553693
+#> iter 5 value 899.826852
+#> iter 6 value 899.416093
+#> iter 7 value 899.408733
+#> iter 7 value 899.408728
+#> iter 7 value 899.408728
+#> final value 899.408728
#> converged
#> This is Run number 2
#> does sou_gis exist: FALSE
@@ -678,37 +678,37 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block
-#> 1 1 9 80 5.0 0 60 20.0 10.0 1
-#> 2 1 12 60 2.5 10 40 20.0 0.0 1
-#> 3 1 13 20 20.0 10 80 2.5 0.0 1
-#> 4 1 70 80 5.0 10 20 20.0 2.5 1
-#> 5 1 71 60 20.0 10 80 10.0 0.0 1
-#> 6 1 73 60 10.0 0 40 20.0 10.0 1
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -1.150 -1.800 3.0041977 0.38322958 1.8541977 -1.4167704 1
-#> 2 1 -0.575 -1.800 3.0101002 0.72197923 2.4351002 -1.0780208 1
-#> 3 1 -1.400 -0.975 1.1260977 0.06998784 -0.2739023 -0.9050122 1
-#> 4 1 -0.950 -1.550 1.9511131 0.39768983 1.0011131 -1.1523102 1
-#> 5 1 -1.800 -1.500 -0.4686622 -0.83175553 -2.2686622 -2.3317555 1
-#> 6 1 -1.300 -1.600 1.5102954 0.98561984 0.2102954 -0.6143802 1
+#> ID Choice_situation alt1_x1 alt1_x2 alt1_x3 alt2_x1 alt2_x2 alt2_x3 Block group V_1 V_2 e_1 e_2 U_1 U_2
+#> 1 1 9 80 5.0 0 60 20.0 10.0 1 1 -1.150 -1.800 -0.55606335 0.4418297 -1.7060633 -1.3581703
+#> 2 1 12 60 2.5 10 40 20.0 0.0 1 1 -0.575 -1.800 -0.70525965 0.3030154 -1.2802596 -1.4969846
+#> 3 1 13 20 20.0 10 80 2.5 0.0 1 1 -1.400 -0.975 0.76358526 1.1547805 -0.6364147 0.1797805
+#> 4 1 70 80 5.0 10 20 20.0 2.5 1 1 -0.950 -1.550 -0.50057341 1.6569802 -1.4505734 0.1069802
+#> 5 1 71 60 20.0 10 80 10.0 0.0 1 1 -1.800 -1.500 0.95196390 4.6640005 -0.8480361 3.1640005
+#> 6 1 73 60 10.0 0 40 20.0 10.0 1 1 -1.300 -1.600 -0.07807331 0.9519585 -1.3780733 -0.6480415
+#> CHOICE
+#> 1 2
+#> 2 1
+#> 3 2
+#> 4 2
+#> 5 2
+#> 6 2
#>
#>
#> This is the utility functions
#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319
#> Initial gradient value:
#> bpreis blade bwarte
-#> -2840.0 -2792.5 980.0
+#> -1480.0 -3742.5 752.5
#> initial value 998.131940
-#> iter 2 value 970.451816
-#> iter 3 value 943.596118
-#> iter 4 value 943.593445
-#> iter 5 value 937.085850
-#> iter 6 value 927.191585
-#> iter 7 value 927.129298
-#> iter 8 value 927.128981
-#> iter 8 value 927.128980
-#> final value 927.128980
+#> iter 2 value 931.326512
+#> iter 3 value 904.389362
+#> iter 4 value 902.747564
+#> iter 5 value 895.585146
+#> iter 6 value 895.212841
+#> iter 7 value 895.208094
+#> iter 7 value 895.208091
+#> iter 7 value 895.208091
+#> final value 895.208091
#> converged
#>
#>
@@ -716,11 +716,11 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> \ vars n mean sd min max range se
#> ================ ==== === ===== ==== ===== ===== ===== ====
#> est_bpreis 1 2 -0.01 0.00 -0.01 -0.01 0.00 0.00
-#> est_blade 2 2 -0.04 0.00 -0.05 -0.04 0.01 0.00
-#> est_bwarte 3 2 0.01 0.00 0.01 0.02 0.00 0.00
+#> est_blade 2 2 -0.05 0.01 -0.05 -0.04 0.01 0.01
+#> est_bwarte 3 2 0.01 0.03 0.00 0.03 0.04 0.02
#> rob_pval0_bpreis 4 2 0.00 0.00 0.00 0.00 0.00 0.00
#> rob_pval0_blade 5 2 0.00 0.00 0.00 0.00 0.00 0.00
-#> rob_pval0_bwarte 6 2 0.05 0.06 0.01 0.09 0.08 0.04
+#> rob_pval0_bwarte 6 2 0.28 0.40 0.00 0.57 0.57 0.28
#> ================ ==== === ===== ==== ===== ===== ===== ====
#>
#> FALSE TRUE
@@ -760,20 +760,20 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation Block alt1_x1 alt2_x1 alt1_x2 alt2_x2 alt1_x3 alt2_x3
-#> 1 1 1 1 80 20 2.5 20.0 10 5
-#> 2 1 2 1 60 40 5.0 10.0 5 10
-#> 3 1 3 1 60 20 20.0 20.0 0 10
-#> 4 1 4 1 20 80 20.0 2.5 0 10
-#> 5 1 5 1 40 80 10.0 5.0 10 5
-#> 6 1 6 1 60 80 5.0 2.5 0 0
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -0.775 -1.500 0.1987193 -1.0900058 -0.5762807 -2.590005753 1
-#> 2 1 -0.850 -0.900 0.2937177 1.3988380 -0.5562823 0.498837973 2
-#> 3 1 -2.000 -1.400 1.2142542 0.5244772 -0.7857458 -0.875522760 1
-#> 4 1 -1.600 -0.775 2.2587676 0.2695545 0.6587676 -0.505445461 1
-#> 5 1 -0.900 -1.050 0.7958478 1.0485339 -0.1041522 -0.001466141 2
-#> 6 1 -0.950 -0.975 0.3019734 -0.4699530 -0.6480266 -1.444953045 1
+#> ID Choice_situation Block alt1_x1 alt2_x1 alt1_x2 alt2_x2 alt1_x3 alt2_x3 group V_1 V_2 e_1 e_2 U_1 U_2
+#> 1 1 1 1 80 20 2.5 20.0 10 5 1 -0.775 -1.500 0.12234341 0.6503776 -0.6526566 -0.84962241
+#> 2 1 2 1 60 40 5.0 10.0 5 10 1 -0.850 -0.900 -0.43360819 0.6615210 -1.2836082 -0.23847900
+#> 3 1 3 1 60 20 20.0 20.0 0 10 1 -2.000 -1.400 -0.31286639 5.7827787 -2.3128664 4.38277870
+#> 4 1 4 1 20 80 20.0 2.5 0 10 1 -1.600 -0.775 -0.15949911 0.6857678 -1.7594991 -0.08923219
+#> 5 1 5 1 40 80 10.0 5.0 10 5 1 -0.900 -1.050 -0.05237788 1.5859039 -0.9523779 0.53590389
+#> 6 1 6 1 60 80 5.0 2.5 0 0 1 -0.950 -0.975 2.34036634 0.2393918 1.3903663 -0.73560816
+#> CHOICE
+#> 1 1
+#> 2 2
+#> 3 2
+#> 4 2
+#> 5 2
+#> 6 1
#>
#>
#> This is Run number 1
@@ -788,36 +788,36 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation Block alt1_x1 alt2_x1 alt1_x2 alt2_x2 alt1_x3 alt2_x3
-#> 1 1 1 1 80 20 2.5 20.0 10 5
-#> 2 1 2 1 60 40 5.0 10.0 5 10
-#> 3 1 3 1 60 20 20.0 20.0 0 10
-#> 4 1 4 1 20 80 20.0 2.5 0 10
-#> 5 1 5 1 40 80 10.0 5.0 10 5
-#> 6 1 6 1 60 80 5.0 2.5 0 0
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -0.775 -1.500 -0.3472514 2.3168155 -1.1222514 0.8168155 2
-#> 2 1 -0.850 -0.900 0.2943507 -1.7082525 -0.5556493 -2.6082525 1
-#> 3 1 -2.000 -1.400 0.4742717 1.1619537 -1.5257283 -0.2380463 2
-#> 4 1 -1.600 -0.775 0.5628095 2.7090502 -1.0371905 1.9340502 2
-#> 5 1 -0.900 -1.050 -0.2128470 -1.3149155 -1.1128470 -2.3649155 1
-#> 6 1 -0.950 -0.975 1.6192730 0.3695527 0.6692730 -0.6054473 1
+#> ID Choice_situation Block alt1_x1 alt2_x1 alt1_x2 alt2_x2 alt1_x3 alt2_x3 group V_1 V_2 e_1 e_2 U_1
+#> 1 1 1 1 80 20 2.5 20.0 10 5 1 -0.775 -1.500 1.74395858 1.6507121 0.968958575
+#> 2 1 2 1 60 40 5.0 10.0 5 10 1 -0.850 -0.900 1.10763894 0.9337414 0.257638936
+#> 3 1 3 1 60 20 20.0 20.0 0 10 1 -2.000 -1.400 -1.23519031 -0.7089281 -3.235190315
+#> 4 1 4 1 20 80 20.0 2.5 0 10 1 -1.600 -0.775 -0.06854059 2.1896932 -1.668540589
+#> 5 1 5 1 40 80 10.0 5.0 10 5 1 -0.900 -1.050 0.90927543 0.3884170 0.009275432
+#> 6 1 6 1 60 80 5.0 2.5 0 0 1 -0.950 -0.975 0.57272851 0.4992305 -0.377271490
+#> U_2 CHOICE
+#> 1 0.15071215 1
+#> 2 0.03374141 1
+#> 3 -2.10892809 2
+#> 4 1.41469320 2
+#> 5 -0.66158301 1
+#> 6 -0.47576952 1
#>
#>
#> This is the utility functions
#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319
#> Initial gradient value:
#> bpreis blade bwarte
-#> -620.0 -877.5 407.5
+#> -880 -830 405
#> initial value 998.131940
-#> iter 2 value 991.196029
-#> iter 3 value 975.595269
-#> iter 4 value 975.571052
-#> iter 5 value 971.582698
-#> iter 6 value 971.577726
-#> iter 6 value 971.577720
-#> iter 6 value 971.577720
-#> final value 971.577720
+#> iter 2 value 994.862696
+#> iter 3 value 973.696602
+#> iter 4 value 973.644209
+#> iter 5 value 971.118222
+#> iter 6 value 971.113908
+#> iter 6 value 971.113906
+#> iter 6 value 971.113906
+#> final value 971.113906
#> converged
#> This is Run number 2
#> does sou_gis exist: FALSE
@@ -831,36 +831,36 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> data has been made
#>
#> First few observations
-#> ID Choice_situation Block alt1_x1 alt2_x1 alt1_x2 alt2_x2 alt1_x3 alt2_x3
-#> 1 1 1 1 80 20 2.5 20.0 10 5
-#> 2 1 2 1 60 40 5.0 10.0 5 10
-#> 3 1 3 1 60 20 20.0 20.0 0 10
-#> 4 1 4 1 20 80 20.0 2.5 0 10
-#> 5 1 5 1 40 80 10.0 5.0 10 5
-#> 6 1 6 1 60 80 5.0 2.5 0 0
-#> group V_1 V_2 e_1 e_2 U_1 U_2 CHOICE
-#> 1 1 -0.775 -1.500 0.5287428 1.2994989 -0.2462572 -0.2005011 2
-#> 2 1 -0.850 -0.900 3.2064378 0.4735037 2.3564378 -0.4264963 1
-#> 3 1 -2.000 -1.400 1.2595242 0.1146570 -0.7404758 -1.2853430 1
-#> 4 1 -1.600 -0.775 4.2748306 -0.7146858 2.6748306 -1.4896858 1
-#> 5 1 -0.900 -1.050 0.1088246 2.2911218 -0.7911754 1.2411218 2
-#> 6 1 -0.950 -0.975 1.1654639 1.3627596 0.2154639 0.3877596 2
+#> ID Choice_situation Block alt1_x1 alt2_x1 alt1_x2 alt2_x2 alt1_x3 alt2_x3 group V_1 V_2 e_1 e_2 U_1 U_2
+#> 1 1 1 1 80 20 2.5 20.0 10 5 1 -0.775 -1.500 -1.1552146 1.6918663 -1.930215 0.1918663
+#> 2 1 2 1 60 40 5.0 10.0 5 10 1 -0.850 -0.900 3.5255143 2.5874719 2.675514 1.6874719
+#> 3 1 3 1 60 20 20.0 20.0 0 10 1 -2.000 -1.400 -0.1288440 3.2280170 -2.128844 1.8280170
+#> 4 1 4 1 20 80 20.0 2.5 0 10 1 -1.600 -0.775 -0.3072974 -0.3710956 -1.907297 -1.1460956
+#> 5 1 5 1 40 80 10.0 5.0 10 5 1 -0.900 -1.050 -0.6042191 -0.1952303 -1.504219 -1.2452303
+#> 6 1 6 1 60 80 5.0 2.5 0 0 1 -0.950 -0.975 -0.6233011 -0.2803958 -1.573301 -1.2553958
+#> CHOICE
+#> 1 2
+#> 2 1
+#> 3 2
+#> 4 2
+#> 5 2
+#> 6 2
#>
#>
#> This is the utility functions
#> U_1 = @bpreis *$alt1_x1 + @blade *$alt1_x2 + @bwarte *$alt1_x3 ;U_2 = @bpreis *$alt2_x1 + @blade *$alt2_x2 + @bwarte *$alt2_x3 ;Initial function value: -998.1319
#> Initial gradient value:
#> bpreis blade bwarte
-#> -580.0 -1077.5 495.0
+#> -1060.0 -832.5 460.0
#> initial value 998.131940
-#> iter 2 value 984.134259
-#> iter 3 value 967.898748
-#> iter 4 value 967.884812
-#> iter 5 value 960.128712
-#> iter 6 value 960.126933
-#> iter 6 value 960.126928
-#> iter 6 value 960.126928
-#> final value 960.126928
+#> iter 2 value 994.307556
+#> iter 3 value 972.255010
+#> iter 4 value 972.242499
+#> iter 5 value 968.104609
+#> iter 6 value 968.103010
+#> iter 6 value 968.103008
+#> iter 6 value 968.103008
+#> final value 968.103008
#> converged
#>
#>
@@ -868,29 +868,29 @@ sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
#> \ vars n mean sd min max range se
#> ================ ==== === ===== ==== ===== ===== ===== ====
#> est_bpreis 1 2 -0.01 0.00 -0.01 -0.01 0.00 0.00
-#> est_blade 2 2 -0.05 0.01 -0.06 -0.05 0.01 0.00
-#> est_bwarte 3 2 0.02 0.00 0.02 0.02 0.01 0.00
+#> est_blade 2 2 -0.05 0.00 -0.05 -0.05 0.00 0.00
+#> est_bwarte 3 2 0.02 0.00 0.01 0.02 0.00 0.00
#> rob_pval0_bpreis 4 2 0.00 0.00 0.00 0.00 0.00 0.00
#> rob_pval0_blade 5 2 0.00 0.00 0.00 0.00 0.00 0.00
-#> rob_pval0_bwarte 6 2 0.11 0.04 0.08 0.13 0.05 0.03
+#> rob_pval0_bwarte 6 2 0.12 0.08 0.06 0.18 0.12 0.06
#> ================ ==== === ===== ==== ===== ===== ===== ====
#>
#> FALSE
#> 100
-#> 32.978 sec elapsed
+#> 9.804 sec elapsed
#> $tic
-#> elapsed
-#> 0.8
+#> elapsed
+#> 10314.36
#>
#> $toc
-#> elapsed
-#> 33.778
+#> elapsed
+#> 10324.16
#>
#> $msg
#> logical(0)
#>
#> $callback_msg
-#> [1] "32.978 sec elapsed"
+#> [1] "9.804 sec elapsed"
```
<img src="man/figures/README-example-1.png" width="100%" /><img src="man/figures/README-example-2.png" width="100%" /><img src="man/figures/README-example-3.png" width="100%" />
diff --git a/man/figures/README-example-1.png b/man/figures/README-example-1.png
index 9d2a3edfa30b18c1fc3ebad59646993121ad0037..f636af7374dc7f8c732b4fcdfdd9dd26b880ffee 100644
Binary files a/man/figures/README-example-1.png and b/man/figures/README-example-1.png differ
diff --git a/man/figures/README-example-2.png b/man/figures/README-example-2.png
index 02013fae37873a26c3aebfdbde76c0eb8e268387..fcd9b871286e73d3b069d55872696893f3c64dc3 100644
Binary files a/man/figures/README-example-2.png and b/man/figures/README-example-2.png differ
diff --git a/man/figures/README-example-3.png b/man/figures/README-example-3.png
index 86086b5a7abb632bc944569de38aee08f99ad634..5c8cdd7080b2322e1c8c200f7e05c649cea48a78 100644
Binary files a/man/figures/README-example-3.png and b/man/figures/README-example-3.png differ
diff --git a/man/sim_all.Rd b/man/sim_all.Rd
index fb98d8e2640c9e694c22da328431668f2119ed27..4b5e8930d8fb91c9e9ac84c63df2ad3879024589 100644
--- a/man/sim_all.Rd
+++ b/man/sim_all.Rd
@@ -2,7 +2,8 @@
% Please edit documentation in R/sim_all.R
\name{sim_all}
\alias{sim_all}
-\title{Is a wrapper for sim_choice executing the simulation over all designs stored in a specific folder}
+\title{Is a wrapper for sim_choice executing the simulation over all designs stored in a specific folder
+update}
\usage{
sim_all(nosim = 2, resps, destype = "ngene", designpath, u, bcoeff)
}
@@ -24,6 +25,7 @@ A list, with all information on the simulation. This list an be easily processed
}
\description{
Is a wrapper for sim_choice executing the simulation over all designs stored in a specific folder
+update
}
\examples{
diff --git a/tests/manual-tests/SE_Drive.R b/tests/manual-tests/SE_Drive.R
index 33c5a0791c435c62147f1cb49b5348e0d22376d9..e5d644deea9838a0f7cd0cb9aa96fa70df0a13cb 100644
--- a/tests/manual-tests/SE_Drive.R
+++ b/tests/manual-tests/SE_Drive.R
@@ -11,11 +11,6 @@ designpath<- system.file("extdata","SE_DRIVE" ,package = "simulateDCE")
resps =120 # number of respondents
nosim= 2 # number of simulations to run (about 500 is minimum)
-
-
-
-
-
# bpreis = -0.036
# blade = -0.034
# bwarte = -0.049
@@ -25,10 +20,11 @@ decisiongroups=c(0,0.7,1)
# wrong parameters
-#
-bpreis = -0.01
-blade = -0.07
-bwarte = 0.02
+# pass beta coefficients as a list
+ bcoeff <- list(
+ bpreis = -0.01,
+ blade = -0.07,
+ bwarte = 0.02)
manipulations = list(alt1.x2= expr(alt1.x2/10),
alt1.x3= expr(alt1.x3/10),
@@ -55,4 +51,4 @@ ul<-list( u1 =
destype="ngene"
sedrive <- sim_all(nosim = nosim, resps=resps, destype = destype,
- designpath = designpath, u=ul)
+ designpath = designpath, u=ul, bcoeff = bcoeff)
diff --git a/tests/testthat/Rplots.pdf b/tests/testthat/Rplots.pdf
index 9003f1bdf3d2ade490ac90fe7301a5db6f49d843..8809a1169cd18196e4da209f19e222171cef5a32 100644
Binary files a/tests/testthat/Rplots.pdf and b/tests/testthat/Rplots.pdf differ
diff --git a/tests/testthat/test-sim_all.R b/tests/testthat/test-sim_all.R
index 283ef565a904e164fc3f2ca40b657de0b77e45b5..e4e4a9d359c9a1b1bd5aa99da72967bf0da5b383 100644
--- a/tests/testthat/test-sim_all.R
+++ b/tests/testthat/test-sim_all.R
@@ -10,14 +10,6 @@ resps =40 # number of respondents
nosim=2 # number of simulations to run (about 500 is minimum)
#betacoefficients should not include "-"
-bsq=0.00
-bredkite=-0.05
-bdistance=0.50
-bcost=-0.05
-bfarm2=0.25
-bfarm3=0.50
-bheight2=0.25
-bheight3=0.50
bcoeff <-list(bsq=0.00,
bredkite=-0.05,
@@ -39,40 +31,32 @@ ul<- list(u1= list(
)
)
-
-
-
-
-
-test_that(" u is not a list", {
+test_that("u is not a list of lists", {
expect_error(sim_all(nosim = nosim, resps=resps, destype = destype,
- designpath = designpath, u=data.frame(u=" alp")),
- "must be provided and must be a list containing ")
+ designpath = designpath, u=data.frame(u=" alp"), bcoeff = bcoeff),
+ "must be provided and must be a list containing at least one list")
})
test_that("no value provided for utility", {
expect_error(sim_all(nosim = nosim, resps=resps, destype = destype,
- designpath = designpath),
- "must be provided and must be a list containing ")
+ designpath = designpath, bcoeff = bcoeff),
+ "must be provided and must be a list containing at least one list")
})
test_that("wrong designtype", {
expect_error(sim_all(nosim = nosim, resps=resps, destype = "ng",
- designpath = designpath, u=ul),"Invalid value for design. Please provide either 'ngene' or 'spdesign'.")
+ designpath = designpath, u=ul, bcoeff = bcoeff),"Invalid value for design. Please provide either 'ngene' or 'spdesign'.")
})
test_that("folder does not exist", {
expect_error(sim_all(nosim = nosim, resps=resps, destype = destype,
- designpath = system.file("da/bullshit", package = "simulateDCE"), u=ul)
+ designpath = system.file("da/bullshit", package = "simulateDCE"), u=ul, bcoeff = bcoeff)
,
"The folder where your designs are stored does not exist.")
})
-
-
-
test_that("seed setting makes code reproducible", {
set.seed(3333)
bcoeff <-list(bsq=0.00,
@@ -99,9 +83,6 @@ test_that("seed setting makes code reproducible", {
expect_identical(result1[["summaryall"]], result2[["summaryall"]])
})
-
-
-
test_that("No seed setting makes code results different", {
result1 <- sim_all(nosim = nosim, resps = resps, destype = destype, designpath = designpath, u = ul, bcoeff = bcoeff)
@@ -112,3 +93,66 @@ test_that("No seed setting makes code results different", {
expect_failure(expect_identical(result1[["summaryall"]], result2[["summaryall"]]))
})
+
+########### Additional Tests ##############
+test_that("bcoeff is provided", {
+ expect_error(sim_all(nosim = nosim, resps = resps, destype = destype,
+ designpath = designpath, u = ul))
+})
+
+test_that("bcoeff contains valid values", {
+ expect_error(sim_all(nosim = nosim, resps = resps, destype = destype,
+ designpath = designpath, u = ul, bcoeff = list(bsq = "invalid")))
+})
+
+test_that("bcoeff is a list", {
+ expect_error(sim_all(nosim = nosim, resps = resps, destype = destype,
+ designpath = designpath, u = ul, bcoeff = "not a list")
+ )
+})
+
+test_that("B coefficients in the utility functions dont match those in the bcoeff list", {
+ expect_error(sim_all(nosim = nosim, resps=resps, destype = destype,
+ designpath = designpath, u = ul, bcoeff <- list(bWRONG = 0.00)))
+})
+
+test_that("Utility functions are valid", {
+ expect_no_error(eval(ul$u1$v1))
+ expect_no_error(eval(ul$u1$v2))
+})
+
+test_that("Design path must be a valid directory", {
+ # Test case: designpath is not a character string
+ expect_error(sim_all(nosim = nosim, resps = resps, destype = destype, designpath = 123, u = ul, bcoeff = bcoeff))
+
+ # Test case: designpath does not exist
+ expect_error(sim_all(nosim = nosim, resps = resps, destype = destype, designpath = '/nonexistent/path', u = ul, bcoeff = bcoeff))
+
+ # Test case: designpath is not a directory
+ expect_error(sim_all(nosim = nosim, resps = resps, destype = destype, designpath = 'path/to/a/file.txt', u = ul, bcoeff = bcoeff))
+})
+
+test_that("Resps must be an integer", {
+ # Test case: resps is missing
+ expect_error(sim_all(nosim = nosim, destype = destype, designpath = designpath, u = ul, bcoeff = bcoeff))
+
+ # Test case: resps is not an integer
+ expect_error(sim_all(nosim = nosim, resps = "abc", destype = destype, designpath = designpath, u = ul, bcoeff = bcoeff))
+
+ # Test case: resps is a numeric but not an integer
+ expect_error(sim_all(nosim = nosim, resps = 1.5, destype = destype, designpath = designpath, u = ul, bcoeff = bcoeff))
+
+})
+
+test_that("Function exists in simulateDCE", {
+ expect_true("sim_all" %in% ls("package:simulateDCE"))
+})
+
+test_that("Simulation results are reasonable", {
+
+ result1 <- sim_all(nosim = nosim, resps = resps, destype = destype, designpath = designpath, u = ul, bcoeff = bcoeff)
+
+ expect_gt(result1$est_bsq, -1)
+ expect_lt(result1$est_bsq, 1)
+
+})