Purpose | Samplers | Targets | Protocol | Results | Efficiency | Accuracy | Curved and funnel-shaped targets | Invariance to scale | Strong correlation | Wall-clock time | Discussion | References | Appendix: code
This package is considered a duplicate. The official version of this package is found at:https://rodrigosqrt3.r-universe.dev/Rtwalk
Package: Rtwalk 2.2.0
Rodrigo Fonseca Villa
Rtwalk: An MCMC Sampler Using the t-Walk Algorithm
Implements the t-walk algorithm, a general-purpose, self-adjusting Markov Chain Monte Carlo (MCMC) sampler for continuous distributions as described by Christen & Fox (2010) <doi:10.1214/10-BA603>. The t-walk requires no tuning and is robust for a wide range of target distributions, including high-dimensional and multimodal problems. The sampler is implemented in C++ and validated against a pure R reference implementation of the published algorithm. The package supports reproducible parallel chains, continuation of runs, single transitions for hybrid samplers, and convergence diagnostics following Vehtari et al. (2021) <doi:10.1214/20-BA1221>.
Authors:
Rtwalk_2.2.0.tar.gz
Rtwalk_2.2.0.zip(r-4.7-x86_64)Rtwalk_2.2.0.zip(r-4.7-arm64)Rtwalk_2.2.0.zip(r-4.6-x86_64)Rtwalk_2.2.0.zip(r-4.6-arm64)
Rtwalk_2.2.0.tar.gz(r-4.7-arm64)Rtwalk_2.2.0.tar.gz(r-4.7-x86_64)Rtwalk_2.2.0.tar.gz(r-4.6-arm64)Rtwalk_2.2.0.tar.gz(r-4.6-x86_64)
Rtwalk_2.2.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
Rtwalk/json (API)
| # Install 'Rtwalk' in R: |
| install.packages('Rtwalk', repos = c('https://cran.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/rodrigosqrt3/rtwalk/issues
Last updated from:84410ea4c7. Checks:10 OK. Indexed: no.
| Target | Result | Time | Files | Syslog |
|---|---|---|---|---|
| linux-devel-arm64 | OK | 163 | ||
| linux-devel-x86_64 | OK | 153 | ||
| source / vignettes | OK | 251 | ||
| linux-release-arm64 | OK | 114 | ||
| linux-release-x86_64 | OK | 126 | ||
| windows-devel-arm64 | OK | 201 | ||
| windows-devel-x86_64 | OK | 156 | ||
| windows-release-arm64 | OK | 251 | ||
| windows-release-x86_64 | OK | 121 | ||
| wasm-release | OK | 115 |
Exports:calculate_diagnosticstwalktwalk_continuetwalk_controltwalk_stepvisualize_results
Benchmarking the t-walk against other general-purpose samplers
Last update: 2026-10-30
Started: 2026-10-30
Reproducing Christen & Fox (2010)
1. Where each piece of the paper lives in the code | 2. The proposal distributions | The Traverse move (Section 2.2, Figure 1) | The Walk move (Section 2.1) | The Hop and Blow moves (Section 2.3) | 3. Invariance (Section 2.6, Theorem 1) | 4. Two-dimensional examples (Section 3.1) | Figure 2 | Figure 3 | 5. Comparison with optimally tuned Metropolis (Section 4, Figure 5) | 6. Acceptance rates | 7. What is not reproduced | References
Last update: 2026-10-30
Started: 2026-10-30
Validation and Simulation Study for the Rtwalk Package
1. A first example: the standard normal | 2. Correlated bivariate normal, four chains | 3. A constrained parameter: Gamma posterior | 4. Ten correlated dimensions | 5. Bayesian logistic regression | 6. Continuing a run | 7. Interoperability | 8. How the two points and the rates are reported
Last update: 2026-10-30
Started: 2026-02-02
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Calculate MCMC diagnostics | calculate_diagnostics |
| Convert t-walk output to coda objects | as.mcmc.list.twalk as.mcmc.twalk coda-methods |
| Plot t-walk output | plot.twalk |
| Convert t-walk output to posterior draws objects | as_draws.twalk as_draws_array.twalk as_draws_df.twalk posterior-methods |
| Run the t-walk MCMC Algorithm | twalk |
| Continue a t-walk run | twalk_continue |
| Control parameters for the t-walk | twalk_control |
| Perform a single t-walk transition | twalk_step |
| Methods for objects of class 'twalk' | print.summary.twalk print.twalk summary.twalk twalk-methods |
| Visualize MCMC results | visualize_results |