R Tutorial With Bayesian Statistics Using Stan

This ebook provides R tutorials on statistics including hypothesis testing, linear regressions, and ANOVA. Its immediate purpose is to fulfill popular demands by users of r-tutor.com for exercise solutions and offline access. In addition, the text also provides an elementary introduction to Bayesian statistics.

Part III of the text is about Bayesian inference using Stan. It is a C++ library that implements the new No-U-Turn Sampler (NUTS) algorithm. Compared with the Gibbs sampling algorithm, the new algorithm converges much more quickly in high-dimensional models without much necessity of conjugate priors. It is a significant improvement of the Random Walk Metropolis-Hastings Markov Chain Monte Carlo (MCMC) algorithm. The ebook then concludes with a discussion of advanced GPU computing using the RPUDPLUS package.

The ebook is for sale at Amazon. You can download the R source code of the tutorials and exercise solutions here.

     r-tutorial-v3a-src-20200612.zip

The R source code of the previous OpenBUGS version of the ebook is r-tutorial-v2c-src-20140321.zip.