Package index • RprobitB

Data management

Use these functions for the choice data preparation or simulation.

check_form(): Check model formula

overview_effects(): Print effect overview

create_lagged_cov(): Create lagged choice covariates

as_cov_names(): Re-label alternative specific covariates

prepare_data(): Prepare choice data for estimation

RprobitB_parameter() print(<RprobitB_parameter>): Define probit model parameter

simulate_choices(): Simulate choice data

train_test(): Split choice data into train and test subset

RprobitB_data() print(<RprobitB_data>) summary(<RprobitB_data>) print(<summary.RprobitB_data>) plot(<RprobitB_data>): Create object of class RprobitB_data

Model fitting

Use these function for fitting a probit model to choice data.

check_prior(): Check prior parameters

fit_model(): Fit probit model to choice data

update(<RprobitB_fit>): Update and re-fit probit model

transform(<RprobitB_fit>): Transform fitted probit model

Model evaluation

Use these functions for model evaluation.

coef(<RprobitB_fit>) print(<RprobitB_coef>) plot(<RprobitB_coef>): Extract model effects

cov_mix(): Extract estimated covariance matrix of mixing distribution

point_estimates(): Compute point estimates

choice_probabilities(): Compute choice probabilities

classification(): Preference-based classification of deciders

get_cov(): Extract covariates of choice occasion

predict(<RprobitB_fit>): Predict choices

plot(<RprobitB_fit>): Visualize fitted probit model

plot_roc(): Plot ROC curve

plot_mixture_contour(): Plot bivariate contour of mixing distributions

plot_class_allocation(): Plot class allocation (for P_r = 2 only)

R_hat(): Compute Gelman-Rubin statistic

mode_approx(): Gibbs sample mode

Model selection

Use these functions for model selection.

model_selection() print(<RprobitB_model_selection>): Compare fitted models

npar(): Extract number of model parameters

mml() print(<RprobitB_mml>) plot(<RprobitB_mml>): Approximate marginal model likelihood

compute_p_si(): Compute choice probabilities at posterior samples

pred_acc(): Compute prediction accuracy

Datasets

The following datasets are included in the package.

train_choice: Stated Preferences for Train Traveling

Posterior samplers

These functions define the Gibbs sampler.

d_to_gamma(): Transform increments to thresholds

gibbs_sampler(): Gibbs sampler for probit models

ll_ordered(): Compute ordered probit log-likelihood

sample_allocation(): Sample allocation

update_Omega(): Update class covariances

update_Omega_c(): Update covariance of a single class

update_Sigma(): Update error covariance matrix

update_U(): Update utility vector

update_U_ranked(): Update ranked utility vector

update_b(): Update class means

update_b_c(): Update mean of a single class

update_classes_dp(): Dirichlet process class updates

update_classes_wb(): Weight-based class updates

update_coefficient(): Update coefficient vector

update_d(): Update utility threshold increments

update_m(): Update class sizes

update_s(): Update class weight vector

update_z(): Update class allocation vector