All Times EDT
Virtual
Overhauling HLMdiag: Updating an R Package to Conform to the Tidyverse (309606)
*Jaylin Lowe, Carleton CollegeAdam Loy, Carleton College
Jack Moran, Carleton College
Keywords: multilevel/hierarchical linear models, diagnostics, R development, tidymodels
Multilevel/hierarchical linear models account for the dependence between observations within the same group in nested data structures. Such models are commonly used to analyze the results of agricultural experiments, longitudinal studies, and educational assessments, to name a few. While model-fitting and inferential procedures are widely implemented for this model class, this is not the case for diagnostic tools. In this presentation, we will provide an overview of the R package HLMdiag, which implements a variety of model diagnostics for this model class, including both residual and influence diagnostics. In particular, we will emphasize how this package was massively overhauled to conform to the tidyverse principles.