A Quick Introduction to Multilevel Bayesian Models for Linguistic Researchers
I’m working on this book for a stats class in the Linguistics department at UC Davis. If you are reading this then I am currently working on it, and it may contain errors, inconsistencies, etc.
This book will focus on a conceptual introduction to multilevel Bayesian models. I am going to talk about ‘math’ as little as possible, so I am going to avoid going into details unless necessary. My goal is to convey some of the more important and useful concepts necessary to understand these models and to use them in your own work. I hope to set you up in a position to ‘fill in the blanks’ as necessary later.
I’m going to try to provide intuitive explanations for statistical models that rely on understanding the figures we use represent and interpret our data and models. The book assumes some understanding of R (only to understand the code), but none of statistics. I don’t really ‘explain’ many basic things, for example, how to calculate a standard deviation? Why is it calculated like it is? There are two reasons for this. First, there are many better resources for that (many written by real statisticians!). And second, I am trying to make this quick, to go from 0 to understanding and interpreting Bayesian multilevel models in 10 weeks.
The book is specifically designed for linguists only because it focuses on the sorts of research designs frequently used by linguists. However, the models and principles outlined in this book are used, and are useful, in many domains.
If you have any comments or suggestions please let me know, and if you find any errors definitely let me know!