A tutorial for estimating mixture models for visual working memory tasks in brms: Introducing the Bayesian Measurement Modeling (bmm) package for R

Abstract

Mixture models for visual working memory tasks using continuous report recall are highly popular measurement models in visual working memory research. Yet, efficient and easy-to-implement estimation procedures that flexibly enable group or condition comparisons are scarce. Specifically, most software packages implementing mixture models have used maximum likelihood estimation for single-subject data. Such estimation procedures require large trial numbers per participant to obtain robust and reliable estimates. This problem can be solved with hierarchical Bayesian estimation procedures that provide robust and reliable estimates with lower trial numbers. In this tutorial, we illustrate how mixture models for visual working memory tasks can be specified and fit in the R package brms. The benefit of this implementation over existing hierarchical Bayesian implementations is that brms integrates hierarchical Bayesian estimation of the mixture models with an efficient linear model syntax that enables us to adapt the mixture model to practically any experimental design. Specifically, this implementation allows varying model parameters over arbitrary groups or experimental conditions. Additionally, the hierarchical structure and the specification of informed priors can improve subject-level parameter estimation and solve estimation problems frequently. We will illustrate these benefits in different examples and provide R code for easy adaptation to other use cases. We also introduce a new R package called bmm, which simplifies the process of estimating these models with brms.