1.3 Tools used in this course
The main programming language used in this course is R (R Core Team 2018). We will make heavy use of the tidyverse package (Wickham 2017), which provides a unified set of functions and conventions that deviate (sometimes: substantially) from basic R. We will also be using the probabilistic programming language WebPPL (Goodman and Stuhlmüller 2014), but only “passively” in order to quickly obtain results from probabilistic calculations that we can experiment with directly in the browser in order to better understand certain ideas or concepts. You will not need to learn to write WebPPL code yourself.
We will rely on the R package brms (Burkner 2017) for running Bayesian generalized regression models, which itself relies on the probabilistic programming language Stan (Carpenter et al. 2017). We will, however, not learn to use Stan in this course, but we will take a glimpse at some Stan code to have seen, at least roughly, where the Markov Chain Monte Carlo samples come from which we will use.
Section 1.6 gives information about how to install the tools necessary for this course.