mxl split

Scripts/mxl/Prediction models/Split_samples/mxl_wtp_space_caseM_Control_Not_Pred.R

+
+#### Apollo standard script #####
+
+library(apollo) # Load apollo package 
+
+data_predictions1 <- readRDS("Data/predictions.RDS")
+data_predictions2 <- readRDS("Data/predictions_labeled.RDS")
+
+data_predictions <- bind_rows(data_predictions1, data_predictions2)
+
+database <- left_join(database_full, data_predictions, by="id")
+
+
+
+database <- database %>% 
+  filter(!is.na(Treatment_new)) %>%
+  mutate(Dummy_Treated = case_when(Treatment_new == 1|Treatment_new == 2  ~ 1, TRUE ~ 0),
+         Dummy_Vol_Treated = case_when(Treatment_new == 5 |Treatment_new == 4 ~ 1, TRUE ~ 0),
+         Dummy_no_info = case_when(Treatment_new == 3 ~ 1, TRUE~0)) %>% 
+  mutate(Dummy_Treated_Pred = case_when(Dummy_Treated == 1 & PredictedGroup == 1 ~1, TRUE~0),
+         Dummy_Treated_Not_Pred = case_when(Dummy_Treated == 1 & PredictedGroup == 0 ~1, TRUE~0)) %>% 
+  mutate(Dummy_Control_Not_Pred = case_when(Treatment_new == 6 & PredictedGroup == 0 ~1, TRUE~0),
+         Dummy_Opt_Treat_Pred = case_when(Treatment_A == "Vol_Treated" & PredictedGroup == 1 ~1, TRUE~0),
+         Dummy_Opt_Treat_Not_Pred = case_when(Treatment_A == "Vol_Treated" & PredictedGroup == 0 ~1, TRUE~0))
+table(database$Treatment)
+database<- filter(database,Dummy_Control_Not_Pred==1  )
+
+
+
+#initialize model 
+
+apollo_initialise()
+
+
+### Set core controls
+apollo_control = list(
+  modelName  = "MXL_wtp_Control_Not_Pred",
+  modelDescr = "MXL_wtp_Control_Not_Pred",
+  indivID    ="id",
+  mixing     = TRUE,
+  HB= FALSE,
+  nCores     = n_cores, 
+  outputDirectory = "Estimation_results/mxl/prediction/Split_samples"
+)
+
+##### Define model parameters depending on your attributes and model specification! ####
+# set values to 0 for conditional logit model
+
+apollo_beta=c(mu_natural = 15,
+              mu_walking = -1,
+              mu_rent = -2,
+              ASC_sq = 0,
+              sig_natural = 15,
+              sig_walking = 2,
+              sig_rent = 2,
+              sig_ASC_sq = 0)
+
+### specify parameters that should be kept fixed, here = none
+apollo_fixed = c()
+
+### Set parameters for generating draws, use 2000 sobol draws
+apollo_draws = list(
+  interDrawsType = "sobol",
+  interNDraws    = n_draws,
+  interUnifDraws = c(),
+  interNormDraws = c("draws_natural", "draws_walking", "draws_rent", "draws_asc"),
+  intraDrawsType = "halton",
+  intraNDraws    = 0,
+  intraUnifDraws = c(),
+  intraNormDraws = c()
+)
+
+### Create random parameters, define distribution of the parameters
+apollo_randCoeff = function(apollo_beta, apollo_inputs){
+  randcoeff = list()
+  
+  randcoeff[["b_mu_natural"]] = mu_natural + sig_natural * draws_natural
+  randcoeff[["b_mu_walking"]] = mu_walking + sig_walking * draws_walking
+  randcoeff[["b_mu_rent"]] = -exp(mu_rent + sig_rent * draws_rent)
+  randcoeff[["b_ASC_sq"]] = ASC_sq + sig_ASC_sq * draws_asc
+  
+  return(randcoeff)
+}
+
+
+### validate 
+apollo_inputs = apollo_validateInputs()
+apollo_probabilities=function(apollo_beta, apollo_inputs, functionality="estimate"){
+  
+  ### Function initialisation: do not change the following three commands
+  ### Attach inputs and detach after function exit
+  apollo_attach(apollo_beta, apollo_inputs)
+  on.exit(apollo_detach(apollo_beta, apollo_inputs))
+  
+  ### Create list of probabilities P
+  P = list()
+  
+  #### List of utilities (later integrated in mnl_settings below)  ####
+  # Define utility functions here:
+  
+  V = list()
+  V[['alt1']] = -b_mu_rent*(b_mu_natural * Naturalness_1 + b_mu_walking * WalkingDistance_1 -
+                              Rent_1)
+  
+  V[['alt2']] = -b_mu_rent*(b_mu_natural * Naturalness_2 + b_mu_walking * WalkingDistance_2 -
+                              Rent_2)
+  
+  V[['alt3']] = -b_mu_rent*(b_ASC_sq + b_mu_natural * Naturalness_3 + b_mu_walking * WalkingDistance_3 -
+                              Rent_3)
+  
+  
+  ### Define settings for MNL model component
+  mnl_settings = list(
+    alternatives  = c(alt1=1, alt2=2, alt3=3),
+    avail         = 1, # all alternatives are available in every choice
+    choiceVar     = choice,
+    V             = V#,  # tell function to use list vector defined above
+    
+  )
+  
+  ### Compute probabilities using MNL model
+  P[['model']] = apollo_mnl(mnl_settings, functionality)
+  
+  ### Take product across observation for same individual
+  P = apollo_panelProd(P, apollo_inputs, functionality)
+  
+  ### Average across inter-individual draws - nur bei Mixed Logit!
+  P = apollo_avgInterDraws(P, apollo_inputs, functionality)
+  
+  ### Prepare and return outputs of function
+  P = apollo_prepareProb(P, apollo_inputs, functionality)
+  return(P)
+}
+
+
+
+# ################################################################# #
+#### MODEL ESTIMATION                                            ##
+# ################################################################# #
+# estimate model with bfgs algorithm
+
+model = apollo_estimate(apollo_beta, apollo_fixed,
+                        apollo_probabilities, apollo_inputs, 
+                        estimate_settings=list(maxIterations=400,
+                                               estimationRoutine="bfgs",
+                                               hessianRoutine="analytic"))
+
+
+
+# ################################################################# #
+#### MODEL OUTPUTS                                               ##
+# ################################################################# #
+apollo_saveOutput(model)
+
+apollo_modelOutput(model)
+

Scripts/mxl/Prediction models/Split_samples/mxl_wtp_space_caseM_Control_Pred.R

+
+#### Apollo standard script #####
+
+library(apollo) # Load apollo package 
+
+data_predictions1 <- readRDS("Data/predictions.RDS")
+data_predictions2 <- readRDS("Data/predictions_labeled.RDS")
+
+data_predictions <- bind_rows(data_predictions1, data_predictions2)
+
+database <- left_join(database_full, data_predictions, by="id")
+
+
+
+database <- database %>% 
+  filter(!is.na(Treatment_new)) %>%
+  mutate(Dummy_Treated = case_when(Treatment_new == 1|Treatment_new == 2  ~ 1, TRUE ~ 0),
+         Dummy_Vol_Treated = case_when(Treatment_new == 5 |Treatment_new == 4 ~ 1, TRUE ~ 0),
+         Dummy_no_info = case_when(Treatment_new == 3 ~ 1, TRUE~0)) %>% 
+  mutate(Dummy_Treated_Pred = case_when(Dummy_Treated == 1 & PredictedGroup == 1 ~1, TRUE~0),
+         Dummy_Treated_Not_Pred = case_when(Dummy_Treated == 1 & PredictedGroup == 0 ~1, TRUE~0)) %>% 
+  mutate(Dummy_Control_Not_Pred = case_when(Treatment_new == 6 & PredictedGroup == 0 ~1, TRUE~0),
+         Dummy_Opt_Treat_Pred = case_when(Treatment_A == "Vol_Treated" & PredictedGroup == 1 ~1, TRUE~0),
+         Dummy_Opt_Treat_Not_Pred = case_when(Treatment_A == "Vol_Treated" & PredictedGroup == 0 ~1, TRUE~0))
+table(database$Treatment)
+database<- filter(database,Dummy_Control_Not_Pred==0 & Dummy_Treated_Pred==0 & 
+                    Dummy_Treated_Not_Pred == 0 & Dummy_Opt_Treat_Pred==0 &
+                    Dummy_Opt_Treat_Not_Pred == 0)
+
+
+#initialize model 
+
+apollo_initialise()
+
+
+### Set core controls
+apollo_control = list(
+  modelName  = "MXL_wtp_Control_Pred",
+  modelDescr = "MXL_wtp_Control_Pred",
+  indivID    ="id",
+  mixing     = TRUE,
+  HB= FALSE,
+  nCores     = n_cores, 
+  outputDirectory = "Estimation_results/mxl/prediction/Split_samples"
+)
+
+##### Define model parameters depending on your attributes and model specification! ####
+# set values to 0 for conditional logit model
+
+apollo_beta=c(mu_natural = 15,
+              mu_walking = -1,
+              mu_rent = -2,
+              ASC_sq = 0,
+              sig_natural = 15,
+              sig_walking = 2,
+              sig_rent = 2,
+              sig_ASC_sq = 0)
+
+### specify parameters that should be kept fixed, here = none
+apollo_fixed = c()
+
+### Set parameters for generating draws, use 2000 sobol draws
+apollo_draws = list(
+  interDrawsType = "sobol",
+  interNDraws    = n_draws,
+  interUnifDraws = c(),
+  interNormDraws = c("draws_natural", "draws_walking", "draws_rent", "draws_asc"),
+  intraDrawsType = "halton",
+  intraNDraws    = 0,
+  intraUnifDraws = c(),
+  intraNormDraws = c()
+)
+
+### Create random parameters, define distribution of the parameters
+apollo_randCoeff = function(apollo_beta, apollo_inputs){
+  randcoeff = list()
+  
+  randcoeff[["b_mu_natural"]] = mu_natural + sig_natural * draws_natural
+  randcoeff[["b_mu_walking"]] = mu_walking + sig_walking * draws_walking
+  randcoeff[["b_mu_rent"]] = -exp(mu_rent + sig_rent * draws_rent)
+  randcoeff[["b_ASC_sq"]] = ASC_sq + sig_ASC_sq * draws_asc
+  
+  return(randcoeff)
+}
+
+
+### validate 
+apollo_inputs = apollo_validateInputs()
+apollo_probabilities=function(apollo_beta, apollo_inputs, functionality="estimate"){
+  
+  ### Function initialisation: do not change the following three commands
+  ### Attach inputs and detach after function exit
+  apollo_attach(apollo_beta, apollo_inputs)
+  on.exit(apollo_detach(apollo_beta, apollo_inputs))
+  
+  ### Create list of probabilities P
+  P = list()
+  
+  #### List of utilities (later integrated in mnl_settings below)  ####
+  # Define utility functions here:
+  
+  V = list()
+  V[['alt1']] = -b_mu_rent*(b_mu_natural * Naturalness_1 + b_mu_walking * WalkingDistance_1 -
+                              Rent_1)
+  
+  V[['alt2']] = -b_mu_rent*(b_mu_natural * Naturalness_2 + b_mu_walking * WalkingDistance_2 -
+                              Rent_2)
+  
+  V[['alt3']] = -b_mu_rent*(b_ASC_sq + b_mu_natural * Naturalness_3 + b_mu_walking * WalkingDistance_3 -
+                              Rent_3)
+  
+  
+  ### Define settings for MNL model component
+  mnl_settings = list(
+    alternatives  = c(alt1=1, alt2=2, alt3=3),
+    avail         = 1, # all alternatives are available in every choice
+    choiceVar     = choice,
+    V             = V#,  # tell function to use list vector defined above
+    
+  )
+  
+  ### Compute probabilities using MNL model
+  P[['model']] = apollo_mnl(mnl_settings, functionality)
+  
+  ### Take product across observation for same individual
+  P = apollo_panelProd(P, apollo_inputs, functionality)
+  
+  ### Average across inter-individual draws - nur bei Mixed Logit!
+  P = apollo_avgInterDraws(P, apollo_inputs, functionality)
+  
+  ### Prepare and return outputs of function
+  P = apollo_prepareProb(P, apollo_inputs, functionality)
+  return(P)
+}
+
+
+
+# ################################################################# #
+#### MODEL ESTIMATION                                            ##
+# ################################################################# #
+# estimate model with bfgs algorithm
+
+model = apollo_estimate(apollo_beta, apollo_fixed,
+                        apollo_probabilities, apollo_inputs, 
+                        estimate_settings=list(maxIterations=400,
+                                               estimationRoutine="bfgs",
+                                               hessianRoutine="analytic"))
+
+
+
+# ################################################################# #
+#### MODEL OUTPUTS                                               ##
+# ################################################################# #
+apollo_saveOutput(model)
+
+apollo_modelOutput(model)
+

Scripts/mxl/Prediction models/Split_samples/mxl_wtp_space_caseM_Opt_Not_Pred.R

+
+#### Apollo standard script #####
+
+library(apollo) # Load apollo package 
+
+data_predictions1 <- readRDS("Data/predictions.RDS")
+data_predictions2 <- readRDS("Data/predictions_labeled.RDS")
+
+data_predictions <- bind_rows(data_predictions1, data_predictions2)
+
+database <- left_join(database_full, data_predictions, by="id")
+
+
+
+database <- database %>% 
+  filter(!is.na(Treatment_new)) %>%
+  mutate(Dummy_Treated = case_when(Treatment_new == 1|Treatment_new == 2  ~ 1, TRUE ~ 0),
+         Dummy_Vol_Treated = case_when(Treatment_new == 5 |Treatment_new == 4 ~ 1, TRUE ~ 0),
+         Dummy_no_info = case_when(Treatment_new == 3 ~ 1, TRUE~0)) %>% 
+  mutate(Dummy_Treated_Pred = case_when(Dummy_Treated == 1 & PredictedGroup == 1 ~1, TRUE~0),
+         Dummy_Treated_Not_Pred = case_when(Dummy_Treated == 1 & PredictedGroup == 0 ~1, TRUE~0)) %>% 
+  mutate(Dummy_Control_Not_Pred = case_when(Treatment_new == 6 & PredictedGroup == 0 ~1, TRUE~0),
+         Dummy_Opt_Treat_Pred = case_when(Treatment_A == "Vol_Treated" & PredictedGroup == 1 ~1, TRUE~0),
+         Dummy_Opt_Treat_Not_Pred = case_when(Treatment_A == "Vol_Treated" & PredictedGroup == 0 ~1, TRUE~0))
+table(database$Treatment)
+database<- filter(database,Dummy_Opt_Treat_Not_Pred==1  )
+
+
+
+#initialize model 
+
+apollo_initialise()
+
+
+### Set core controls
+apollo_control = list(
+  modelName  = "MXL_wtp_Opt_Not_Pred",
+  modelDescr = "MXL_wtp_Opt_Not_Pred",
+  indivID    ="id",
+  mixing     = TRUE,
+  HB= FALSE,
+  nCores     = n_cores, 
+  outputDirectory = "Estimation_results/mxl/prediction/Split_samples"
+)
+
+##### Define model parameters depending on your attributes and model specification! ####
+# set values to 0 for conditional logit model
+
+apollo_beta=c(mu_natural = 15,
+              mu_walking = -1,
+              mu_rent = -2,
+              ASC_sq = 0,
+              sig_natural = 15,
+              sig_walking = 2,
+              sig_rent = 2,
+              sig_ASC_sq = 0)
+
+### specify parameters that should be kept fixed, here = none
+apollo_fixed = c()
+
+### Set parameters for generating draws, use 2000 sobol draws
+apollo_draws = list(
+  interDrawsType = "sobol",
+  interNDraws    = n_draws,
+  interUnifDraws = c(),
+  interNormDraws = c("draws_natural", "draws_walking", "draws_rent", "draws_asc"),
+  intraDrawsType = "halton",
+  intraNDraws    = 0,
+  intraUnifDraws = c(),
+  intraNormDraws = c()
+)
+
+### Create random parameters, define distribution of the parameters
+apollo_randCoeff = function(apollo_beta, apollo_inputs){
+  randcoeff = list()
+  
+  randcoeff[["b_mu_natural"]] = mu_natural + sig_natural * draws_natural
+  randcoeff[["b_mu_walking"]] = mu_walking + sig_walking * draws_walking
+  randcoeff[["b_mu_rent"]] = -exp(mu_rent + sig_rent * draws_rent)
+  randcoeff[["b_ASC_sq"]] = ASC_sq + sig_ASC_sq * draws_asc
+  
+  return(randcoeff)
+}
+
+
+### validate 
+apollo_inputs = apollo_validateInputs()
+apollo_probabilities=function(apollo_beta, apollo_inputs, functionality="estimate"){
+  
+  ### Function initialisation: do not change the following three commands
+  ### Attach inputs and detach after function exit
+  apollo_attach(apollo_beta, apollo_inputs)
+  on.exit(apollo_detach(apollo_beta, apollo_inputs))
+  
+  ### Create list of probabilities P
+  P = list()
+  
+  #### List of utilities (later integrated in mnl_settings below)  ####
+  # Define utility functions here:
+  
+  V = list()
+  V[['alt1']] = -b_mu_rent*(b_mu_natural * Naturalness_1 + b_mu_walking * WalkingDistance_1 -
+                              Rent_1)
+  
+  V[['alt2']] = -b_mu_rent*(b_mu_natural * Naturalness_2 + b_mu_walking * WalkingDistance_2 -
+                              Rent_2)
+  
+  V[['alt3']] = -b_mu_rent*(b_ASC_sq + b_mu_natural * Naturalness_3 + b_mu_walking * WalkingDistance_3 -
+                              Rent_3)
+  
+  
+  ### Define settings for MNL model component
+  mnl_settings = list(
+    alternatives  = c(alt1=1, alt2=2, alt3=3),
+    avail         = 1, # all alternatives are available in every choice
+    choiceVar     = choice,
+    V             = V#,  # tell function to use list vector defined above
+    
+  )
+  
+  ### Compute probabilities using MNL model
+  P[['model']] = apollo_mnl(mnl_settings, functionality)
+  
+  ### Take product across observation for same individual
+  P = apollo_panelProd(P, apollo_inputs, functionality)
+  
+  ### Average across inter-individual draws - nur bei Mixed Logit!
+  P = apollo_avgInterDraws(P, apollo_inputs, functionality)
+  
+  ### Prepare and return outputs of function
+  P = apollo_prepareProb(P, apollo_inputs, functionality)
+  return(P)
+}
+
+
+
+# ################################################################# #
+#### MODEL ESTIMATION                                            ##
+# ################################################################# #
+# estimate model with bfgs algorithm
+
+model = apollo_estimate(apollo_beta, apollo_fixed,
+                        apollo_probabilities, apollo_inputs, 
+                        estimate_settings=list(maxIterations=400,
+                                               estimationRoutine="bfgs",
+                                               hessianRoutine="analytic"))
+
+
+
+# ################################################################# #
+#### MODEL OUTPUTS                                               ##
+# ################################################################# #
+apollo_saveOutput(model)
+
+apollo_modelOutput(model)
+

Scripts/mxl/Prediction models/Split_samples/mxl_wtp_space_caseM_Opt_Pred.R

+
+#### Apollo standard script #####
+
+library(apollo) # Load apollo package 
+
+data_predictions1 <- readRDS("Data/predictions.RDS")
+data_predictions2 <- readRDS("Data/predictions_labeled.RDS")
+
+data_predictions <- bind_rows(data_predictions1, data_predictions2)
+
+database <- left_join(database_full, data_predictions, by="id")
+
+
+
+database <- database %>% 
+  filter(!is.na(Treatment_new)) %>%
+  mutate(Dummy_Treated = case_when(Treatment_new == 1|Treatment_new == 2  ~ 1, TRUE ~ 0),
+         Dummy_Vol_Treated = case_when(Treatment_new == 5 |Treatment_new == 4 ~ 1, TRUE ~ 0),
+         Dummy_no_info = case_when(Treatment_new == 3 ~ 1, TRUE~0)) %>% 
+  mutate(Dummy_Treated_Pred = case_when(Dummy_Treated == 1 & PredictedGroup == 1 ~1, TRUE~0),
+         Dummy_Treated_Not_Pred = case_when(Dummy_Treated == 1 & PredictedGroup == 0 ~1, TRUE~0)) %>% 
+  mutate(Dummy_Control_Not_Pred = case_when(Treatment_new == 6 & PredictedGroup == 0 ~1, TRUE~0),
+         Dummy_Opt_Treat_Pred = case_when(Treatment_A == "Vol_Treated" & PredictedGroup == 1 ~1, TRUE~0),
+         Dummy_Opt_Treat_Not_Pred = case_when(Treatment_A == "Vol_Treated" & PredictedGroup == 0 ~1, TRUE~0))
+table(database$Treatment)
+database<- filter(database,Dummy_Opt_Treat_Pred==1  )
+
+
+
+#initialize model 
+
+apollo_initialise()
+
+
+### Set core controls
+apollo_control = list(
+  modelName  = "MXL_wtp_Opt_Pred",
+  modelDescr = "MXL_wtp_Opt_Pred",
+  indivID    ="id",
+  mixing     = TRUE,
+  HB= FALSE,
+  nCores     = n_cores, 
+  outputDirectory = "Estimation_results/mxl/prediction/Split_samples"
+)
+
+##### Define model parameters depending on your attributes and model specification! ####
+# set values to 0 for conditional logit model
+
+apollo_beta=c(mu_natural = 15,
+              mu_walking = -1,
+              mu_rent = -2,
+              ASC_sq = 0,
+              sig_natural = 15,
+              sig_walking = 2,
+              sig_rent = 2,
+              sig_ASC_sq = 0)
+
+### specify parameters that should be kept fixed, here = none
+apollo_fixed = c()
+
+### Set parameters for generating draws, use 2000 sobol draws
+apollo_draws = list(
+  interDrawsType = "sobol",
+  interNDraws    = n_draws,
+  interUnifDraws = c(),
+  interNormDraws = c("draws_natural", "draws_walking", "draws_rent", "draws_asc"),
+  intraDrawsType = "halton",
+  intraNDraws    = 0,
+  intraUnifDraws = c(),
+  intraNormDraws = c()
+)
+
+### Create random parameters, define distribution of the parameters
+apollo_randCoeff = function(apollo_beta, apollo_inputs){
+  randcoeff = list()
+  
+  randcoeff[["b_mu_natural"]] = mu_natural + sig_natural * draws_natural
+  randcoeff[["b_mu_walking"]] = mu_walking + sig_walking * draws_walking
+  randcoeff[["b_mu_rent"]] = -exp(mu_rent + sig_rent * draws_rent)
+  randcoeff[["b_ASC_sq"]] = ASC_sq + sig_ASC_sq * draws_asc
+  
+  return(randcoeff)
+}
+
+
+### validate 
+apollo_inputs = apollo_validateInputs()
+apollo_probabilities=function(apollo_beta, apollo_inputs, functionality="estimate"){
+  
+  ### Function initialisation: do not change the following three commands
+  ### Attach inputs and detach after function exit
+  apollo_attach(apollo_beta, apollo_inputs)
+  on.exit(apollo_detach(apollo_beta, apollo_inputs))
+  
+  ### Create list of probabilities P
+  P = list()
+  
+  #### List of utilities (later integrated in mnl_settings below)  ####
+  # Define utility functions here:
+  
+  V = list()
+  V[['alt1']] = -b_mu_rent*(b_mu_natural * Naturalness_1 + b_mu_walking * WalkingDistance_1 -
+                              Rent_1)
+  
+  V[['alt2']] = -b_mu_rent*(b_mu_natural * Naturalness_2 + b_mu_walking * WalkingDistance_2 -
+                              Rent_2)
+  
+  V[['alt3']] = -b_mu_rent*(b_ASC_sq + b_mu_natural * Naturalness_3 + b_mu_walking * WalkingDistance_3 -
+                              Rent_3)
+  
+  
+  ### Define settings for MNL model component
+  mnl_settings = list(
+    alternatives  = c(alt1=1, alt2=2, alt3=3),
+    avail         = 1, # all alternatives are available in every choice
+    choiceVar     = choice,
+    V             = V#,  # tell function to use list vector defined above
+    
+  )
+  
+  ### Compute probabilities using MNL model
+  P[['model']] = apollo_mnl(mnl_settings, functionality)
+  
+  ### Take product across observation for same individual
+  P = apollo_panelProd(P, apollo_inputs, functionality)
+  
+  ### Average across inter-individual draws - nur bei Mixed Logit!
+  P = apollo_avgInterDraws(P, apollo_inputs, functionality)
+  
+  ### Prepare and return outputs of function
+  P = apollo_prepareProb(P, apollo_inputs, functionality)
+  return(P)
+}
+
+
+
+# ################################################################# #
+#### MODEL ESTIMATION                                            ##
+# ################################################################# #
+# estimate model with bfgs algorithm
+
+model = apollo_estimate(apollo_beta, apollo_fixed,
+                        apollo_probabilities, apollo_inputs, 
+                        estimate_settings=list(maxIterations=400,
+                                               estimationRoutine="bfgs",
+                                               hessianRoutine="analytic"))
+
+
+
+# ################################################################# #
+#### MODEL OUTPUTS                                               ##
+# ################################################################# #
+apollo_saveOutput(model)
+
+apollo_modelOutput(model)
+

Scripts/mxl/Prediction models/Split_samples/mxl_wtp_space_caseM_Treatment_Not_Pred.R

+
+#### Apollo standard script #####
+
+library(apollo) # Load apollo package 
+
+data_predictions1 <- readRDS("Data/predictions.RDS")
+data_predictions2 <- readRDS("Data/predictions_labeled.RDS")
+
+data_predictions <- bind_rows(data_predictions1, data_predictions2)
+
+database <- left_join(database_full, data_predictions, by="id")
+
+
+
+database <- database %>% 
+  filter(!is.na(Treatment_new)) %>%
+  mutate(Dummy_Treated = case_when(Treatment_new == 1|Treatment_new == 2  ~ 1, TRUE ~ 0),
+         Dummy_Vol_Treated = case_when(Treatment_new == 5 |Treatment_new == 4 ~ 1, TRUE ~ 0),
+         Dummy_no_info = case_when(Treatment_new == 3 ~ 1, TRUE~0)) %>% 
+  mutate(Dummy_Treated_Pred = case_when(Dummy_Treated == 1 & PredictedGroup == 1 ~1, TRUE~0),
+         Dummy_Treated_Not_Pred = case_when(Dummy_Treated == 1 & PredictedGroup == 0 ~1, TRUE~0)) %>% 
+  mutate(Dummy_Control_Not_Pred = case_when(Treatment_new == 6 & PredictedGroup == 0 ~1, TRUE~0),
+         Dummy_Opt_Treat_Pred = case_when(Treatment_A == "Vol_Treated" & PredictedGroup == 1 ~1, TRUE~0),
+         Dummy_Opt_Treat_Not_Pred = case_when(Treatment_A == "Vol_Treated" & PredictedGroup == 0 ~1, TRUE~0))
+table(database$Treatment)
+database<- filter(database,Dummy_Treated_Not_Pred==1  )
+
+
+
+#initialize model 
+
+apollo_initialise()
+
+
+### Set core controls
+apollo_control = list(
+  modelName  = "MXL_wtp_Treated_Not_Pred",
+  modelDescr = "MXL_wtp_Treated_Not_Pred",
+  indivID    ="id",
+  mixing     = TRUE,
+  HB= FALSE,
+  nCores     = n_cores, 
+  outputDirectory = "Estimation_results/mxl/prediction/Split_samples"
+)
+
+##### Define model parameters depending on your attributes and model specification! ####
+# set values to 0 for conditional logit model
+
+apollo_beta=c(mu_natural = 15,
+              mu_walking = -1,
+              mu_rent = -2,
+              ASC_sq = 0,
+              sig_natural = 15,
+              sig_walking = 2,
+              sig_rent = 2,
+              sig_ASC_sq = 0)
+
+### specify parameters that should be kept fixed, here = none
+apollo_fixed = c()
+
+### Set parameters for generating draws, use 2000 sobol draws
+apollo_draws = list(
+  interDrawsType = "sobol",
+  interNDraws    = n_draws,
+  interUnifDraws = c(),
+  interNormDraws = c("draws_natural", "draws_walking", "draws_rent", "draws_asc"),
+  intraDrawsType = "halton",
+  intraNDraws    = 0,
+  intraUnifDraws = c(),
+  intraNormDraws = c()
+)
+
+### Create random parameters, define distribution of the parameters
+apollo_randCoeff = function(apollo_beta, apollo_inputs){
+  randcoeff = list()
+  
+  randcoeff[["b_mu_natural"]] = mu_natural + sig_natural * draws_natural
+  randcoeff[["b_mu_walking"]] = mu_walking + sig_walking * draws_walking
+  randcoeff[["b_mu_rent"]] = -exp(mu_rent + sig_rent * draws_rent)
+  randcoeff[["b_ASC_sq"]] = ASC_sq + sig_ASC_sq * draws_asc
+  
+  return(randcoeff)
+}
+
+
+### validate 
+apollo_inputs = apollo_validateInputs()
+apollo_probabilities=function(apollo_beta, apollo_inputs, functionality="estimate"){
+  
+  ### Function initialisation: do not change the following three commands
+  ### Attach inputs and detach after function exit
+  apollo_attach(apollo_beta, apollo_inputs)
+  on.exit(apollo_detach(apollo_beta, apollo_inputs))
+  
+  ### Create list of probabilities P
+  P = list()
+  
+  #### List of utilities (later integrated in mnl_settings below)  ####
+  # Define utility functions here:
+  
+  V = list()
+  V[['alt1']] = -b_mu_rent*(b_mu_natural * Naturalness_1 + b_mu_walking * WalkingDistance_1 -
+                              Rent_1)
+  
+  V[['alt2']] = -b_mu_rent*(b_mu_natural * Naturalness_2 + b_mu_walking * WalkingDistance_2 -
+                              Rent_2)
+  
+  V[['alt3']] = -b_mu_rent*(b_ASC_sq + b_mu_natural * Naturalness_3 + b_mu_walking * WalkingDistance_3 -
+                              Rent_3)
+  
+  
+  ### Define settings for MNL model component
+  mnl_settings = list(
+    alternatives  = c(alt1=1, alt2=2, alt3=3),
+    avail         = 1, # all alternatives are available in every choice
+    choiceVar     = choice,
+    V             = V#,  # tell function to use list vector defined above
+    
+  )
+  
+  ### Compute probabilities using MNL model
+  P[['model']] = apollo_mnl(mnl_settings, functionality)
+  
+  ### Take product across observation for same individual
+  P = apollo_panelProd(P, apollo_inputs, functionality)
+  
+  ### Average across inter-individual draws - nur bei Mixed Logit!
+  P = apollo_avgInterDraws(P, apollo_inputs, functionality)
+  
+  ### Prepare and return outputs of function
+  P = apollo_prepareProb(P, apollo_inputs, functionality)
+  return(P)
+}
+
+
+
+# ################################################################# #
+#### MODEL ESTIMATION                                            ##
+# ################################################################# #
+# estimate model with bfgs algorithm
+
+model = apollo_estimate(apollo_beta, apollo_fixed,
+                        apollo_probabilities, apollo_inputs, 
+                        estimate_settings=list(maxIterations=400,
+                                               estimationRoutine="bfgs",
+                                               hessianRoutine="analytic"))
+
+
+
+# ################################################################# #
+#### MODEL OUTPUTS                                               ##
+# ################################################################# #
+apollo_saveOutput(model)
+
+apollo_modelOutput(model)
+

Scripts/mxl/Prediction models/Split_samples/mxl_wtp_space_caseM_Treatment_Pred.R

+
+#### Apollo standard script #####
+
+library(apollo) # Load apollo package 
+
+data_predictions1 <- readRDS("Data/predictions.RDS")
+data_predictions2 <- readRDS("Data/predictions_labeled.RDS")
+
+data_predictions <- bind_rows(data_predictions1, data_predictions2)
+
+database <- left_join(database_full, data_predictions, by="id")
+
+
+
+database <- database %>% 
+  filter(!is.na(Treatment_new)) %>%
+  mutate(Dummy_Treated = case_when(Treatment_new == 1|Treatment_new == 2  ~ 1, TRUE ~ 0),
+         Dummy_Vol_Treated = case_when(Treatment_new == 5 |Treatment_new == 4 ~ 1, TRUE ~ 0),
+         Dummy_no_info = case_when(Treatment_new == 3 ~ 1, TRUE~0)) %>% 
+  mutate(Dummy_Treated_Pred = case_when(Dummy_Treated == 1 & PredictedGroup == 1 ~1, TRUE~0),
+         Dummy_Treated_Not_Pred = case_when(Dummy_Treated == 1 & PredictedGroup == 0 ~1, TRUE~0)) %>% 
+  mutate(Dummy_Control_Not_Pred = case_when(Treatment_new == 6 & PredictedGroup == 0 ~1, TRUE~0),
+         Dummy_Opt_Treat_Pred = case_when(Treatment_A == "Vol_Treated" & PredictedGroup == 1 ~1, TRUE~0),
+         Dummy_Opt_Treat_Not_Pred = case_when(Treatment_A == "Vol_Treated" & PredictedGroup == 0 ~1, TRUE~0))
+table(database$Treatment)
+database<- filter(database,Dummy_Treated_Pred==1  )
+
+
+
+#initialize model 
+
+apollo_initialise()
+
+
+### Set core controls
+apollo_control = list(
+  modelName  = "MXL_wtp_Treated_Pred",
+  modelDescr = "MXL_wtp_Treated_Pred",
+  indivID    ="id",
+  mixing     = TRUE,
+  HB= FALSE,
+  nCores     = n_cores, 
+  outputDirectory = "Estimation_results/mxl/prediction/Split_samples"
+)
+
+##### Define model parameters depending on your attributes and model specification! ####
+# set values to 0 for conditional logit model
+
+apollo_beta=c(mu_natural = 15,
+              mu_walking = -1,
+              mu_rent = -2,
+              ASC_sq = 0,
+              sig_natural = 15,
+              sig_walking = 2,
+              sig_rent = 2,
+              sig_ASC_sq = 0)
+
+### specify parameters that should be kept fixed, here = none
+apollo_fixed = c()
+
+### Set parameters for generating draws, use 2000 sobol draws
+apollo_draws = list(
+  interDrawsType = "sobol",
+  interNDraws    = n_draws,
+  interUnifDraws = c(),
+  interNormDraws = c("draws_natural", "draws_walking", "draws_rent", "draws_asc"),
+  intraDrawsType = "halton",
+  intraNDraws    = 0,
+  intraUnifDraws = c(),
+  intraNormDraws = c()
+)
+
+### Create random parameters, define distribution of the parameters
+apollo_randCoeff = function(apollo_beta, apollo_inputs){
+  randcoeff = list()
+  
+  randcoeff[["b_mu_natural"]] = mu_natural + sig_natural * draws_natural
+  randcoeff[["b_mu_walking"]] = mu_walking + sig_walking * draws_walking
+  randcoeff[["b_mu_rent"]] = -exp(mu_rent + sig_rent * draws_rent)
+  randcoeff[["b_ASC_sq"]] = ASC_sq + sig_ASC_sq * draws_asc
+  
+  return(randcoeff)
+}
+
+
+### validate 
+apollo_inputs = apollo_validateInputs()
+apollo_probabilities=function(apollo_beta, apollo_inputs, functionality="estimate"){
+  
+  ### Function initialisation: do not change the following three commands
+  ### Attach inputs and detach after function exit
+  apollo_attach(apollo_beta, apollo_inputs)
+  on.exit(apollo_detach(apollo_beta, apollo_inputs))
+  
+  ### Create list of probabilities P
+  P = list()
+  
+  #### List of utilities (later integrated in mnl_settings below)  ####
+  # Define utility functions here:
+  
+  V = list()
+  V[['alt1']] = -b_mu_rent*(b_mu_natural * Naturalness_1 + b_mu_walking * WalkingDistance_1 -
+                              Rent_1)
+  
+  V[['alt2']] = -b_mu_rent*(b_mu_natural * Naturalness_2 + b_mu_walking * WalkingDistance_2 -
+                              Rent_2)
+  
+  V[['alt3']] = -b_mu_rent*(b_ASC_sq + b_mu_natural * Naturalness_3 + b_mu_walking * WalkingDistance_3 -
+                              Rent_3)
+  
+  
+  ### Define settings for MNL model component
+  mnl_settings = list(
+    alternatives  = c(alt1=1, alt2=2, alt3=3),
+    avail         = 1, # all alternatives are available in every choice
+    choiceVar     = choice,
+    V             = V#,  # tell function to use list vector defined above
+    
+  )
+  
+  ### Compute probabilities using MNL model
+  P[['model']] = apollo_mnl(mnl_settings, functionality)
+  
+  ### Take product across observation for same individual
+  P = apollo_panelProd(P, apollo_inputs, functionality)
+  
+  ### Average across inter-individual draws - nur bei Mixed Logit!
+  P = apollo_avgInterDraws(P, apollo_inputs, functionality)
+  
+  ### Prepare and return outputs of function
+  P = apollo_prepareProb(P, apollo_inputs, functionality)
+  return(P)
+}
+
+
+
+# ################################################################# #
+#### MODEL ESTIMATION                                            ##
+# ################################################################# #
+# estimate model with bfgs algorithm
+
+model = apollo_estimate(apollo_beta, apollo_fixed,
+                                   apollo_probabilities, apollo_inputs, 
+                                   estimate_settings=list(maxIterations=400,
+                                                          estimationRoutine="bfgs",
+                                                          hessianRoutine="analytic"))
+
+
+
+# ################################################################# #
+#### MODEL OUTPUTS                                               ##
+# ################################################################# #
+apollo_saveOutput(model)
+
+apollo_modelOutput(model)
+

Scripts/visualize_distr_spli.R

+# Load models
+MXL_wtp_Control_Not_Pred_model <- readRDS("C:/nextcloud/Hot_Topic_Cool_Choices/Estimation_results/mxl/prediction/Split_samples/MXL_wtp_Control_Not_Pred_model.rds")
+MXL_wtp_Control_Pred_model <- readRDS("C:/nextcloud/Hot_Topic_Cool_Choices/Estimation_results/mxl/prediction/Split_samples/MXL_wtp_Control_Pred_model.rds")
+MXL_wtp_Opt_Not_Pred_model <- readRDS("C:/nextcloud/Hot_Topic_Cool_Choices/Estimation_results/mxl/prediction/Split_samples/MXL_wtp_Opt_Not_Pred_model.rds")
+MXL_wtp_Opt_Pred_model <- readRDS("C:/nextcloud/Hot_Topic_Cool_Choices/Estimation_results/mxl/prediction/Split_samples/MXL_wtp_Opt_Pred_model.rds")
+MXL_wtp_Treated_Not_Pred_model <- readRDS("C:/nextcloud/Hot_Topic_Cool_Choices/Estimation_results/mxl/prediction/Split_samples/MXL_wtp_Treated_Not_Pred_model.rds")
+MXL_wtp_Treated_Pred_model <- readRDS("C:/nextcloud/Hot_Topic_Cool_Choices/Estimation_results/mxl/prediction/Split_samples/MXL_wtp_Treated_Pred_model.rds")
+
+# List of models
+models <- list(
+  "Treated Not Pred" = MXL_wtp_Treated_Not_Pred_model,
+  "Control Not Pred" = MXL_wtp_Control_Not_Pred_model,
+  "Control Pred" = MXL_wtp_Control_Pred_model,
+  "Opt Not Pred" = MXL_wtp_Opt_Not_Pred_model,
+  "Opt Pred" = MXL_wtp_Opt_Pred_model,
+  "Treated Pred" = MXL_wtp_Treated_Pred_model
+)
+
+# Define the x-range for plotting (1000 values)
+x_range <- seq(-10, 100, length.out = 1000)
+
+# Define colors and line types for each model
+colors <- c("blue", "red", "green", "purple", "orange", "brown")
+line_types <- 1:6
+
+# Initialize the plot with the first model
+model <- models[["Treated Not Pred"]]
+coef <- summary(model)$estimate
+mean <- coef["mu_natural", "Estimate"]
+sd <- coef["sig_natural", "Estimate"]
+y <- dnorm(x_range, mean, sd)
+
+plot(x_range, y, type = "l", col = colors[1], lwd = 2, lty = line_types[1],
+     ylim = c(0, max(y)), xlab = "x", ylab = "Density", 
+     main = "Normal Distributions from Multiple MXL Models")
+
+# Loop through the remaining models and add their distributions to the plot
+for (i in 2:length(models)) {
+  model <- models[[i]]
+  
+  # Extract mean and standard deviation for 'mu_natural' and 'sig_natural'
+  coef <- summary(model)$estimate
+  mean <- coef["mu_natural", "Estimate"]
+  sd <- coef["sig_natural", "Estimate"]
+  
+  # Compute the normal distribution based on extracted mean and sd
+  y <- dnorm(x_range, mean, sd)
+  
+  # Add the distribution to the existing plot
+  lines(x_range, y, col = colors[i], lwd = 2, lty = line_types[i])
+}
+
+# Add a legend
+legend("topright", inset = c(-0.25, 0), legend = names(models), col = colors, 
+       lty = line_types, lwd = 2, xpd = TRUE)