Package index • choicer

Model fitting

Estimate a discrete-choice model.

run_mnlogit(): Runs multinomial logit estimation
run_mxlogit(): Runs mixed logit estimation
run_nestlogit(): Runs nested logit estimation
run_mnprobit(): Runs Bayesian multinomial probit estimation
run_hmnlogit(): Fit a hierarchical Bayesian multinomial logit (HMNL)
run_hmnprobit(): Fit a hierarchical Bayesian multinomial probit (HMNP)

Data preparation

Build design matrices and inputs for the estimators.

prepare_mnl_data(): Prepare inputs for multinomial logit estimation
prepare_mxl_data(): Prepare inputs for mixed logit estimation
prepare_nl_data(): Prepare inputs for nested logit estimation
prepare_mnp_data(): Prepare inputs for Bayesian multinomial probit estimation
prepare_hmnl_data(): Prepare inputs for hierarchical multinomial logit estimation
prepare_hmnp_data(): Prepare inputs for hierarchical multinomial probit estimation

Demand and substitution

Predicted shares, elasticities, diversion and share inversion.

predict(<choicer_hb>): Posterior choice probabilities and shares for hierarchical Bayes fits
predict(<choicer_mnl>): Predict from a multinomial logit model
predict(<choicer_mxl>): Predict from a mixed logit model
predict(<choicer_nl>): Predict from a nested logit model
elasticities(): Compute aggregate elasticities
elasticities(<choicer_mnl>): Elasticities for multinomial logit model
elasticities(<choicer_mxl>): Elasticities for mixed logit model
elasticities(<choicer_nl>): Elasticities for nested logit model
diversion_ratios(): Compute aggregate diversion ratios
diversion_ratios(<choicer_mnl>): Diversion ratios for multinomial logit model
diversion_ratios(<choicer_mxl>): Diversion ratios for mixed logit model
diversion_ratios(<choicer_nl>): Diversion ratios for nested logit model
blp(): BLP contraction mapping
blp(<choicer_mnl>): BLP contraction mapping for multinomial logit model
blp(<choicer_mxl>): BLP contraction mapping for mixed logit model
blp(<choicer_nl>): BLP contraction mapping for nested logit model
blp_contraction(): BLP95 contraction mapping to find delta given target shares

Welfare

Willingness-to-pay and consumer surplus.

wtp(): Compute willingness to pay
consumer_surplus(): Expected consumer surplus
logsum(): Expected logsum (inclusive value) per choice situation

Goodness of fit and methods

gof(): Goodness of fit for a fitted choice model
summary(<choicer_hb>): Summarize a hierarchical Bayes fit
summary(<choicer_mnl>): Summary for multinomial logit model
summary(<choicer_mnp>): Summary for Bayesian multinomial probit model
summary(<choicer_mxl>): Summary for mixed logit model
summary(<choicer_nl>): Summary for nested logit model
coef(<choicer_fit>): Extract coefficients from a choicer_fit object
coef(<choicer_hb>): Extract posterior means from a hierarchical Bayes fit
coef(<choicer_mnp>): Extract coefficients from a choicer_mnp object
vcov(<choicer_fit>): Extract variance-covariance matrix from a choicer_fit object
vcov(<choicer_hb>): Posterior covariance of the population coefficients
vcov(<choicer_mnp>): Extract variance-covariance matrix from a choicer_mnp object
logLik(<choicer_fit>): Extract log-likelihood from a choicer_fit object
nobs(<choicer_fit>): Extract number of observations from a choicer_fit object
nobs(<choicer_hb>): Number of choice situations behind a hierarchical Bayes fit
nobs(<choicer_mnp>): Extract number of observations from a choicer_mnp object
print(<choicer_cs>): Print a consumer surplus summary
print(<choicer_fit>): Print a choicer_fit object
print(<choicer_gof>): Print goodness-of-fit measures
print(<choicer_hb>): Print a hierarchical Bayes fit
print(<choicer_mnp>): Print a choicer_mnp object
print(<choicer_wtp>): Print a WTP table
print(<summary.choicer_hb>): Print the summary of a hierarchical Bayes fit
print(<summary.choicer_mnl>): Print summary for multinomial logit model
print(<summary.choicer_mnp>): Print summary for Bayesian multinomial probit model
print(<summary.choicer_mxl>): Print summary for mixed logit model
print(<summary.choicer_nl>): Print summary for nested logit model
rhat(): Split-\(\widehat{R}\) convergence diagnostic
ppc_shares(): Posterior-predictive share check for hierarchical Bayes fits
ess(): Rank-normalized effective sample size (bulk and tail)
mcse(): Monte Carlo standard error of posterior summaries
traceplot(): Traceplot for a hierarchical Bayes fit
traceplot(<choicer_hb>): Traceplot method for hierarchical Bayes fits

Simulation and recovery

Data-generating processes and parameter-recovery diagnostics.

simulate_mnl_data(): Simulate multinomial logit data
simulate_mxl_data(): Simulate mixed logit data
simulate_nl_data(): Simulate nested logit data
simulate_mnp_data(): Simulate multinomial probit data
simulate_hmnl_data(): Simulate hierarchical multinomial logit data
simulate_hmnp_data(): Simulate hierarchical multinomial probit data
recovery_table(): Parameter recovery table
monte_carlo(): Monte Carlo parameter recovery
mc_asymptotics(): Asymptotic diagnostics for a Monte Carlo study
new_choicer_sim(): Construct a choicer_sim object

Choice-based sampling

wesml_weights(): WESML weights for choice-based (endogenous stratified) samples
sample_by_choice(): Draw a choice-based sample stratified by the chosen alternative
wesml_vcov(): Robust (sandwich) variance for a weighted / choice-based logit fit

Configuration and helpers

set_num_threads(): Set the number of OpenMP threads used by choicer
thread_info(): Query choicer OpenMP thread settings
get_halton_normals(): Halton draws for mixed logit
mxl_blp_contraction(): BLP contraction mapping for mixed logit
nl_blp_contraction(): BLP95 contraction mapping for the Nested Logit model

Data

mode_choice: Intercity travel mode choice