Название: Bayesian Structural Equation Modeling
Автор: Sarah Depaoli
Издательство: The Guilford Press
Год: 2021
Страниц: 550
Язык: английский
Формат: pdf (true)
Размер: 12.0 MB

This book offers researchers a systematic and accessible introduction to using a Bayesian framework in structural equation modeling (SEM). Stand-alone chapters on each SEM model clearly explain the Bayesian form of the model and walk the reader through implementation. Engaging worked-through examples from diverse social science subfields illustrate the various modeling techniques, highlighting statistical or estimation problems that are likely to arise and describing potential solutions. For each model, instructions are provided for writing up findings for publication, including annotated sample data analysis plans and results sections. Other user-friendly features in every chapter include "Major Take-Home Points," notation glossaries, annotated suggestions for further reading, and excerpts of annotated code in both Mplus and R. The companion website supplies datasets, code, and output for all of the book’s examples.

Each year in the last decade or so, more and more packages in R have been published that allow for Bayesian implementation or provide graphical resources. Being that R is free and relatively easy to use given the extensive online documentation, it is a desirable choice for Bayesian implementation. Programs that can be implemented in R, such as Stan and Blavaan, have provided relatively straightforward implementation of Bayesian methods to a variety of model types. Applied users no longer have to rely on learning a complex new programming language to implement Bayesian methods - and the days of requesting an annual “key” from the BUGS group are behind us.

With an increase in application, we have also seen an increase in tutorials and other discussions surrounding the benefits and extensions that Bayesian statistics afford latent variable modeling. Indeed, Bayesian methods offer a more flexible alternative to their frequentist counterparts. Many of these elements of flexibility are illustrated throughout this book. Bayesian statistics are, no doubt, an attractive alternative to implementing SEMs.

To date, there are still very few books tackling Bayesian SEM, and most are written at a more technical level. The goal of this book is to introduce Bayesian SEM to graduate students and researchers in the social and behavioral sciences. This book was written for social and behavioral scientists who are trained in “traditional” statistical methods but want to venture out and explore advanced implementations of SEM through the Bayesian framework.