之前用过这个包中的几种MCMC方法,感觉还是很好用的。现在来总结一下目前这个包中含有的功能模块,顺便复习一下贝叶斯统计学的相关知识点。这个包更新还是挺快的,比一年前多了好多东西,内容很多,无法一次写完,因此本文会不断更新。
Sampler statistics
Diagnosing Biased Inference with Divergences:
- 各态历经(ergodicity)
- geometric ergodicity
- 算例:The Eight Schools Model
- Dangerously-Short Markov Chain
- 算例:Non-Centered Eight Schools Implementation
Posterior Predictive Checks
Model comparison:
- Akaike’s Information Criterion (AIC)
- Deviance Information Criterion (DIC)
- Widely-applicable Information Criterion (WAIC)
- Leave-one-out Cross-validation (LOO)
Model averaging:
- Bayesian Model Averaging
- Pseudo Bayesian model averaging
- Pseudo Bayesian model averaging with Bayesian Bootstrapping
- Stacking
- Weighted posterior predictive samples
- continuous