Year: 2016
Type: preprint
Abstract: The popularity of Bayesian statistical methods has increased dramatically among psychologists in recent years; however, many common types of mixed effects models remain difficult to fit in a Bayesian setting. Here we introduce an opensource Python package named Bambi (BAyesian Model Building Interface) that is built on top of the powerful PyMC3 probabilistic programming framework and makes it easy to specify complex generalized linear mixed effects models using a formula notation similar to those found in packages like lme4 and nlme. We demonstrate Bambi’s versatility and ease-of-use by applying it to three social and personality psychology datasets that span a range of common statistical modelsincluding multiple regression, logistic regression, and mixedeffects modeling with crossed random effects. We conclude with a discussion of the strengths and weaknesses of a Bayesian approach in the context of common statistical practice in psychology.
Authors: Tal Yarkoni, Jake Westfall
Institution: The University of Texas at Austin
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4409673601