airt: Evaluation of Algorithm Collections Using Item Response Theory

An evaluation framework for algorithm portfolios using Item Response Theory (IRT). We use continuous and polytomous IRT models to evaluate algorithms and introduce algorithm characteristics such as stability, effectiveness and anomalousness (Kandanaarachchi, Smith-Miles 2020) <doi:10.13140/RG.2.2.11363.09760>.

Version: 0.2.1
Depends: R (≥ 3.4.0)
Imports: pracma, mirt, tidyr, EstCRM, rlang, dplyr, magrittr, tibble
Suggests: knitr, rmarkdown, ggplot2, gridExtra, scales
Published: 2021-12-17
Author: Sevvandi Kandanaarachchi ORCID iD [aut, cre]
Maintainer: Sevvandi Kandanaarachchi <sevvandik at gmail.com>
License: GPL-3
URL: https://sevvandi.github.io/airt/
NeedsCompilation: no
Materials: README
CRAN checks: airt results

Documentation:

Reference manual: airt.pdf
Vignettes: Introduction to airt

Downloads:

Package source: airt_0.2.1.tar.gz
Windows binaries: r-devel: airt_0.2.1.zip, r-release: airt_0.2.1.zip, r-oldrel: airt_0.2.1.zip
macOS binaries: r-release (arm64): airt_0.2.1.tgz, r-oldrel (arm64): airt_0.2.1.tgz, r-release (x86_64): airt_0.2.1.tgz, r-oldrel (x86_64): airt_0.2.1.tgz
Old sources: airt archive

Reverse dependencies:

Reverse imports: outlierensembles

Linking:

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