Bayesian Probit Choice Modeling
Overview
Fits Bayesian probit models for binary, multinomial, ordered, and ranked choices in cross-sectional and panel data. Correlated or uncorrelated normal and log-normal random coefficients, finite mixtures, sparse finite mixtures, and Dirichlet process mixtures describe preference heterogeneity. Multiple Gibbs chains produce posterior draws for diagnostics and choice prediction. Choice data can be supplied as a data frame or simulated from the requested specification. For an overarching treatment of the methodology, see Oelschlaeger (2026) https://pub.uni-bielefeld.de/record/3014719. The latent-class model is described in Oelschlaeger and Bauer (2021) https://trid.trb.org/view/1759753.
plot()has the new optiontype = "mixture", which draws the estimated mixing distributions of the random effects.bayes_factor()now accepts models with a fixed number of up to six latent classes.- Ordered choice models now include an intercept by default.
- The occupancy table of
latent_class_diagnostics()lists every number of classes from one to the maximum, including numbers with probability zero. - Every chain starts at a draw from the prior distributions of the coefficients and thresholds, with the deciders allocated to the classes at random, instead of at the prior means, so that the chains start dispersed.
- Cap the progress updates to prevent that many fast updates freeze the RStudio console.
From NEWS.md in the release
Install
Health
- OK13 OK2026-09-30
- ERROR11 OK, 2 ERROR2026-09-14
- OK13 OK2026-08-05
- NOTE12 OK, 1 NOTE2026-08-01
- OK13 OK2026-06-09
Show 5 earlier changesHide 5 earlier changes
- ERROR12 OK, 1 ERROR2026-06-08
- OK12 OK2026-04-25
- NOTE12 OK, 2 NOTE2026-04-22
- ERROR11 OK, 2 NOTE, 1 ERROR2026-04-18
- NOTE12 OK, 2 NOTE2026-03-10
Documentation
- Help pages
- 26 (2 internal)includes a package overview page
- Examples that run
- 100%23 run in a plain check (2 of them under a condition)
- Exported functions with examples
- 90%
- Documented parameters
- 96%
- Return-value docs
- 90%
- Help pages citing references
- 38% with a bibliography file
Downloads
Repository
- PRs merged (all time)
- 95%
- Median days to close, 50 most recently updated closed issues
- 30
- Median days to close, 50 most recently updated closed PRs
- 0
Stars over time
Issues over time
PRs over time
Commits over time
13 development-tooling and community-health practices detected across 7 families in the upstream repository
Checks run against github.com/loelschlaeger/rprobitb on 2026-10-18.
The R CMD check workflow runs on Linux, macOS and Windows, and on R-devel
GitHub Pages site last deployed 2026-09-20 · The repository has a site deploy workflow
pkgdown site last built 2026-09-20, before release 2.0.1 (2026-10-21)
Show all practicesHide 3 practices
Dependencies
Code & Tests
People & History
Pick two releases to compare their code metrics.
- 2.0.1Latest
- 2.0.02026-09-20 · diff ↗ ·
removed 24 exports
R_hat, RprobitB_parameter, as_cov_names, check_prior, choice_probabilities, classification, compute_p_si, cov_mix, create_lagged_cov, fit_model, get_cov, ll_ordered, mml, mode_approx, model_selection, npar, overview_effects, plot_class_allocation, plot_mixture_contour, plot_roc, point_estimates, pred_acc, prepare_data, simulate_choicesadded 6 exports
bayes_factor, fit, interpret, latent_class_diagnostics, log_likelihood_ordered, loo - RR 4.6.0 released · 2026-04-24
- 1.2.02025-08-25 · diff ↗ ·
removed 8 exports
dmvnorm, euc_dist, rdirichlet, rmvnorm, rtnorm, rttnorm, rwishart, update_regadded 9 exports
mode_approx, plot_class_allocation, plot_mixture_contour, sample_allocation, update_Omega_c, update_b_c, update_classes_dp, update_classes_wb, update_coefficient - RR 4.5.0 released · 2025-04-11
- RR 4.4.0 released · 2024-04-24
- unarchivedReturned to CRAN2024-02-26
- 1.1.42024-02-26 · diff ↗
- archivedRemoved from CRAN2024-02-21requires archived package 'oeli'
- 1.1.3
- RR 4.3.0 released · 2023-04-21
- 1.1.22022-11-06 · diff ↗
- 1.1.12022-08-11 · diff ↗
- 1.1.02022-07-22 · diff ↗ ·
removed 12 exports
choice_probs, classify, compare, compute_log_likelihood, mcmc, predict, prepare, simulate, transform, is_covariance_matrix, set_mfrow, undiff_Sigmaadded 40 exports
M, RprobitB_parameter, WAIC, as_cov_names, check_prior, choice_probabilities, classification, compute_p_si, cov_mix, create_lagged_cov, d_to_gamma, dmvnorm, euc_dist, fit_model, get_cov, ll_ordered, mml, model_selection, npar, plot_roc, point_estimates, pred_acc, prepare_data, rdirichlet, rmvnorm, rtnorm, rttnorm, rwishart, simulate_choices, train_test and 10 more - RR 4.2.0 released · 2022-04-22
- 1.0.02021-11-12 · diff ↗ ·
removed 1 export
pattern:^[[:alpha:]]+added 15 exports
choice_probs, classify, compare, compute_log_likelihood, mcmc, overview_effects, predict, prepare, simulate, transform, delta, is_covariance_matrix, R_hat, set_mfrow, undiff_Sigma
Package metadata
- First published
- 2021-05-15
- Total releases
- 11 / 5 yrs
- License
- GPL-3 OSI
- Minimum R
- ≥ 4.1.0
- Download size
- 963 KB
Cite
Cite this package
Run in R for the authors' preferred citation:
citation("RprobitB")This package has no citation file, so citation() returns this entry built from DESCRIPTION.
Cite the R Observatory
For a number measured here: a download total, a coverage figure, an archival date.
From data release v2026-10-21, which the citation names so these numbers can be found later. More on citing and the projects behind them.