Linear Mixed Models in Linguistics and Psychology: A Comprehensive Introduction (DRAFT)
This book (once completed! :) is intended to be a relatively complete introduction to the application of linear mixed models in areas related to linguistics and psychology; throughout, we use the programming language R. Our target audience is cognitive scientists (e.g., linguists and psychologists) who carry out behavioral experiments, and who are interested in learning the foundational ideas behind modern statistical methodology from the ground up and in a principled manner.
Many excellent introductory textbooks already exist that discuss data analysis in great detail. Our book is different from existing books in two respects. First, our main focus is on showing how to analyze data from planned experiments involving repeated measures; this type of experimental data involves complexities that are distinct from the problems one encounters when analyzing observational data. We aim to provide many examples, with different types of dependent measures collected in a variety of experimental paradigms, including eyetracking data (visual world and reading experiments), response time data (e.g., self-paced reading, picture naming), event-related potential data, ratings (e.g., acceptability ratings), yes/no responses (e.g., speeded grammaticality judgements), and accuracy data. Second, from the very outset, we stress a particular workflow that has as its centerpiece data simulation; we aim to teach a philosophy that involves thinking about the assumed underlying generative process, even before the data are collected. By the “generative process”, we mean the underlying assumptions about the “process” that produced the data; what exactly this means will presently become clear. The data analysis approach that we hope to teach through this book (once this book is in its final form) involves a cycle of experiment design analysis and model validation using simulated data.