How does it handle model selection?

The skill implements state-of-the-art methods like LOO-CV (Leave-One-Out Cross-Validation), WAIC, and model stacking to compare and weight different models.

Does it help with MCMC convergence diagnostics?

Absolutely. It provides code for visualizing trace plots, calculating R-hat values, checking effective sample size (ESS), and diagnosing divergences.

Which R packages does this skill support?

It primarily supports brms, rstanarm, bayesplot, loo, bridgesampling, and tidybayes for a complete Bayesian workflow.

Can I specify custom priors for my parameters?

Yes, it provides a detailed syntax for setting custom priors on specific coefficients, intercepts, and standard deviations to incorporate domain expertise.

Can I use this for mixed-effects models?

Yes, it includes patterns for random intercepts, random slopes, and crossed random effects using standard lme4-style formulas within a Bayesian framework.

Bayesian Modeling in R

Name: Bayesian Modeling in R
Author: choxos

bychoxos

Data Science & ML

Builds and analyzes robust Bayesian statistical models using Stan-based R packages like brms and rstanarm.

About

This skill empowers Claude to perform high-level Bayesian statistical modeling within the R ecosystem, leveraging the power of Stan through user-friendly interfaces like brms and rstanarm. It provides a structured workflow for specifying complex models—including linear, logistic, mixed-effects, and non-linear architectures—defining custom priors, conducting posterior predictive checks, and performing rigorous model comparison using LOO and WAIC. It is an essential tool for data scientists and researchers who need to quantify uncertainty and incorporate domain knowledge into their statistical analyses while following modern Bayesian workflow best practices.

Key Features

Detailed MCMC diagnostics including trace plots, R-hat, and effective sample size
Advanced prior specification and prior predictive check implementations
0 GitHub stars
Automated setup for Bayesian regression using brms and rstanarm syntax
Comprehensive posterior analysis including credible intervals and hypothesis testing
Model comparison tools using LOO-CV, WAIC, and Bayes Factors

Use Cases

Performing rigorous statistical inference with quantified uncertainty for complex research data
Implementing custom Bayesian workflows that incorporate informative priors and posterior predictive checks
Comparing multiple hierarchical or mixed-effect models to identify the best fit for nested data structures

About

Key Features

Detailed MCMC diagnostics including trace plots, R-hat, and effective sample size
Advanced prior specification and prior predictive check implementations
0 GitHub stars
Automated setup for Bayesian regression using brms and rstanarm syntax
Comprehensive posterior analysis including credible intervals and hypothesis testing
Model comparison tools using LOO-CV, WAIC, and Bayes Factors

Use Cases

Performing rigorous statistical inference with quantified uncertainty for complex research data
Implementing custom Bayesian workflows that incorporate informative priors and posterior predictive checks
Comparing multiple hierarchical or mixed-effect models to identify the best fit for nested data structures