emIRT: EM Algorithms for Estimating Item Response Theory Models

Various Expectation-Maximization (EM) algorithms are implemented for item response theory (IRT) models. The current implementation includes IRT models for binary and ordinal responses, along with dynamic and hierarchical IRT models with binary responses. The latter two models are derived and implemented using variational EM. Subsequent edits also include variational network and text scaling models.

Version: 0.0.8
Depends: R (≥ 2.10), pscl (≥ 1.0.0), Rcpp (≥ 0.10.6)
LinkingTo: Rcpp, RcppArmadillo
Published: 2017-02-14
Author: Kosuke Imai, James Lo, Jonathan Olmsted
Maintainer: James Lo <lojames at usc.edu>
License: GPL (≥ 3)
NeedsCompilation: yes
Materials: ChangeLog
In views: Psychometrics
CRAN checks: emIRT results

Downloads:

Reference manual: emIRT.pdf
Package source: emIRT_0.0.8.tar.gz
Windows binaries: r-devel: emIRT_0.0.8.zip, r-release: emIRT_0.0.8.zip, r-oldrel: emIRT_0.0.8.zip
OS X Mavericks binaries: r-release: emIRT_0.0.8.tgz, r-oldrel: emIRT_0.0.8.tgz
Old sources: emIRT archive

Linking:

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