R package for partitioning generalized linear mixed-effects regression (glmer) models. Available from CRAN (stable release) and R-Forge (development version). For more info, see Fokkema et al. (2018; Behavior Research Methods) for a more technical explanation, Fokkema et al. (2021; Psychotherapy Research) for an introduction aimed at researchers in psychology, or check out the tutorial by typing in R:
install.packages("glmertree") ## stable release from CRAN
install.packages("glmertree", repos="http://R-Forge.R-project.org") ## devel version
An R package for fitting prediction rule ensembles. It implements the method of Friedman and Popescu (2008) with several improvement. E.g., it employs an unbiased algorithms for rule induction; it supports continuous, binary, multinomial, count, multivariate and survival responses; it provides more control over sparsity of the final ensemble; it allows for plotting the ensemble. The package is available from CRAN (stable release) and GitHub (development version). For more info, see Fokkema (2020; Journal of Statistical Software) or Fokkema & Strobl (2020; Psychological Methods or arXiv version for free access) or check out this short tutorial.
curtail: An R package for test curtailment. A curtailed test is a variable-length test, allowing for early stopping of item administration when further items are unlikely or unable to change the final (classification) decision. The package supports deterministic and stochastic (based on empirical proportions) curtailment. It is available on GitHub. The package can be installed and loaded in R as follows: