For my PhD thesis, I’m working on a technique called the Cluster Bootstrap. It encompasses the analysis of clustered data — with a special focus on longitudinal data — by means of generalized linear models and a bootstrap technique. Until now, the output of this research consists of an R package and a paper in Behavior Research Methods.
You can check out the package at my GitHub repository. The package is also available on The Comprehensive R Archive Network (CRAN). In our first paper, we compared the Cluster Bootstrap with generalized linear models to generalized linear mixed models, which is broadly used but relies on assumptions that are difficult to check.
Copyright © 2021 Mathijs Deen.