Expanding the Stan User’s Guide

2026-05-04 · Source: Statistical Modeling, Causal Inference, and Social Science · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Advanced, quick

Summary

The Stan User's Guide, a key resource for the Stan project, has recently received several significant updates and additions. These include new chapters on drift-diffusion Wiener models for reaction-time modeling by Franziska Henrich, multiple imputation by Abner Heredia Bustos, and copulas by Brynjólfur Gauti Guðrúnar Jónsson. Charles Margossian, Steve Bronder, and Aki Vehtari contributed a chapter on embedded Laplace approximation, while Bob added content on survival models. Beyond these major additions, numerous minor clarifications, fixes, and model examples, such as Mitzi Morris's sufficient statistics optimizations, have also been integrated. The documentation's evolution is driven by team interests, new Stan features, and coverage of foundational statistical texts.

Key takeaway

For AI scientists or statisticians utilizing Stan, reviewing the recently added documentation on topics like drift-diffusion Wiener models, multiple imputation, copulas, and embedded Laplace approximation is crucial for staying current with advanced modeling techniques. Consider contributing to the Stan User's Guide yourself, as it offers a valuable opportunity to deepen your understanding and receive expert feedback on complex statistical concepts.

Key insights

The Stan User's Guide is actively expanding with community contributions and new statistical modeling topics.

Principles

• Community contributions enhance documentation quality.
• Writing documentation aids learning complex topics.

In practice

• Explore recent additions to the Stan User's Guide.
• Contribute new chapters to the Stan documentation.

Topics

• Stan User's Guide
• Bayesian Data Analysis
• Drift-diffusion Wiener Models
• Multiple Imputation
• Embedded Laplace Approximation

Code references

• stan-dev/docs

Best for: AI Scientist, Data Scientist, Research Scientist

Related on AIssential

• Full day Stan tutorial at Modern Modeling Methods (M3) this summer in New York (22 June 2026) — The tutorial offers a hands-on introduction to Bayesian modeling and inference with Stan, tailored for psychometric applications.
• Error Bounds for a Diffusion Model-Based Drift Estimator — Theoretical guarantees for a diffusion model-based drift estimator in SDEs are now established through an explicit risk bound.
• SparseNUTS: Preconditioning hierarchical models in HMC with a sparse “Laplace approximation” at the marginal mode — SparseNUTS improves Stan's NUTS efficiency for large hierarchical models by using sparse precision matrix preconditioning.
• Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles — A new framework uses self-supervised principles and a Fisher-based metric (ICR) to evaluate diffusion model representations and detect memorization.
• Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures — URGE improves diffusion model sample quality via derivative-free pathwise importance reweighting and resampling.
• Corrected Integrated Laplace Approximation for Bayesian Inference in Latent Gaussian Models — Importance sampling corrects Integrated Laplace Approximation errors for asymptotically exact Bayesian posteriors in LGMs.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Statistical Modeling, Causal Inference, and Social Science.