This is an experiment in using Discourse topics for documentation as discussed at Discourse - issue/question triage and need for a FAQ the content has yet to receive feedback and tweaks from the broader community. Also, this is a wiki post, so everyone except the very new users of the forum can edit this topic - you are welcome to improve this.
A lot of the content on this forum, Stan documentation and other resources presuppose that readers are at least somewhat familiar with the basics of probability, statistics and Hamiltonian Monte-Carlo computation. We believe that everybody visiting these forums is able to gain understanding those topics in the necessary depth. But we admit that they are not easy.
For users that prefer to set some time aside to read and get better at the basics, we collect a list of resources we believe are a good start.
- Statistical Rethinking by R. McElreath is an introductory book aimed at applied scientists with examples in R. There are also recorded lectures based on the book.
- Case studies by M. Betancourt span from basics of probability theory to model-building workflows in Stan, presuming a familiarity with calculus and linear algebra.
- Bayesian Data Analysis by Gelman et al. is an in-depth treatment of many aspects of Bayesian analysis and modelling. For non-commerical purposes, the book is available online. @avehtari runs a course based on the book and recordings of the lectures and other materials are available from course’s webpage.
Some people might also choose to acquire this knowledge by wrestling with a specific modelling problem they need to solve, Googling a lot and some amount of banging your head against wall/computer monitor or despair. This is also OK, some of the most active community members learned Bayesian statistics this way!
We wish you luck in uncovering the Bayesian mysteries and we firmly believe you can make it. If you are having trouble, don’t be afraid to ask here on Discourse in the “General” category.