Does this skill support censored data?

Yes, it provides specific implementations for handling right-censored data using the log-complementary cumulative distribution function (lccdf) in Stan and the dinterval function in JAGS.

What is the difference between the Stan and JAGS implementations?

Stan implementations utilize Hamiltonian Monte Carlo for faster convergence in complex models, while JAGS patterns use traditional Gibbs sampling, which is sometimes preferred for specific hierarchical structures.

What types of survival models are included?

The skill includes Exponential, Weibull (AFT parameterization), Log-Normal, Piecewise Exponential, and Frailty (random effects) models.

Can I use this for non-proportional hazards?

The Piecewise Exponential model provides a flexible framework that can approximate Cox-like behavior, allowing for more complex hazard shapes than standard parametric models.

Bayesian Survival Models

Name: Bayesian Survival Models
Author: choxos

bychoxos

0•

데이터 과학 및 ML

Implements robust Bayesian survival analysis models including Weibull and Cox-like piecewise hazards with censoring support.

This skill provides a comprehensive library of Bayesian survival analysis patterns for Stan and JAGS, enabling developers and data scientists to model time-to-event data with precision. It covers a wide range of distributions—from simple exponential models to complex frailty and piecewise exponential models—while handling right-censored data and providing tools for calculating hazard ratios and survival functions. It is particularly useful for clinical trials, customer churn prediction, and reliability engineering where uncertainty quantification is critical for decision-making.

주요 기능

01Support for multiple distributions including Exponential, Weibull, and Log-Normal

02Integrated censoring support for both Stan and JAGS implementations

03Generated quantities for hazard ratios and median survival calculations

04Frailty models for handling group-level random effects and unobserved heterogeneity

05Piecewise exponential modeling for flexible Cox-like semi-parametric analysis

060 GitHub stars

사용 사례

01Conducting reliability engineering to estimate failure rates and maintenance schedules for hardware

02Analyzing clinical trial data to determine treatment efficacy and patient survival rates

03Predicting customer churn and lifetime value in subscription-based SaaS environments

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add choxos/bayesianagent survival-models

For use in Claude.ai and ChatGPT

Download Skill