Verified:Website 𝕏@matsilverstein GitHub

pymc-bayesian-modeling

Build PyMC Bayesian models with priors, likelihoods, and posterior inference.

21|2|Updated Dec 8, 2025

Search Tags:#model comparison #pymc #model diagnostics #hierarchical models #bayesian modeling #mcmc nuts #posterior predictive checks

Ready to run

npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill pymc-bayesian-modeling-silverstein

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pymc-bayesian-modeling
Source: https://github.com/silverstein/claude-scientific-skills-desktop/tree/main/corpus/pymc
Command: npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill pymc-bayesian-modeling-silverstein

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

Users need a reliable way to build Bayesian probabilistic models, run inference, and verify that posterior results are trustworthy rather than just plausible.

Core Features & Use Cases

Bayesian modeling workflow for PyMC: Define priors, likelihoods, and model structure for continuous, count, binary, and hierarchical settings.
Inference methods and diagnostics: Run MCMC with NUTS, perform variational inference (ADVI), and check convergence using R-hat, ESS, divergences, and tree depth concepts.
Model validation and comparison: Use prior and posterior predictive checks plus LOO/WAIC-based comparison to select among competing models.

Quick Start

Use the pymc-bayesian-modeling skill to produce a PyMC model specification for your data and explain how to run sampling with NUTS and then perform posterior predictive checks and LOO/WAIC comparison.

Frequently Asked Questions about pymc-bayesian-modeling

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build a hierarchical Bayesian model in PyMC and run inference?▼

Bayesian model comparison uses LOO or WAIC to evaluate predictive accuracy across competing models. These criteria estimate out-of-sample prediction error, helping you select the model that best balances fit and complexity.

What diagnostics should I check to verify PyMC MCMC convergence?▼

Posterior predictive checks in PyMC compare simulated data from your fitted model against observed data to assess model fit. They reveal whether your likelihood and priors adequately capture the underlying data distribution.

Can I use PyMC for uncertainty quantification in time-series-like structures?▼

PyMC supports uncertainty quantification for time-series-like structures by defining probabilistic models with appropriate priors and likelihoods. You can run MCMC or ADVI to estimate posterior distributions and quantify prediction uncertainty.

What is the best way to standardize parameters when defining PyMC priors?▼

Standardizing parameters in PyMC involves centering and scaling predictors to improve MCMC sampling efficiency and convergence. Proper parameterization helps NUTS navigate the posterior geometry, reducing divergences and improving R-hat diagnostics.