mlpwr: A Power Analysis Toolbox to Find Cost-Efficient Study Designs

We implement a surrogate modeling algorithm to guide simulation-based sample size planning. The method is described in detail in a recent preprint (Zimmer & Debelak (2022) <doi:10.31234/osf.io/tnhb2>). It supports multiple study design parameters and optimization with respect to a cost function. It can find optimal designs that correspond to a desired statistical power or that fulfill a cost constraint.

Version: 1.1.0
Depends: R (≥ 2.10)
Imports: utils, stats, DiceKriging, digest, ggplot2, randtoolbox, rlist, WeightSVM, rgenoud
Suggests: knitr, lme4, lmerTest, mirt, pwr, rmarkdown, simr, sn, tidyr
Published: 2023-08-07
Author: Felix Zimmer ORCID iD [aut, cre], Rudolf Debelak ORCID iD [aut]
Maintainer: Felix Zimmer <felix.zimmer at mail.de>
BugReports: https://github.com/flxzimmer/mlpwr/issues
License: GPL (≥ 3)
URL: https://github.com/flxzimmer/mlpwr
NeedsCompilation: no
Materials: README NEWS
CRAN checks: mlpwr results

Documentation:

Reference manual: mlpwr.pdf
Vignettes: extensions
simulation_functions

Downloads:

Package source: mlpwr_1.1.0.tar.gz
Windows binaries: r-devel: mlpwr_1.1.0.zip, r-release: mlpwr_1.1.0.zip, r-oldrel: mlpwr_1.1.0.zip
macOS binaries: r-release (arm64): mlpwr_1.1.0.tgz, r-oldrel (arm64): mlpwr_1.1.0.tgz, r-release (x86_64): mlpwr_1.1.0.tgz
Old sources: mlpwr archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=mlpwr to link to this page.