eRm-package: extended Rasch modeling
Description
This package estimates extended Rasch models, i.e. the
ordinary Rasch model for dichotomous data (RM), the linear logistic test model (LLTM),
the rating scale model (RSM) and its linear extension (LRSM), the partial credit model (PCM)
and its linear extension (LPCM). The parameters are estimated by conditional maximum
likelihood (CML). Missing values are allowed in the data matrix. Additional features
are the estimation of the person parameters, LR-Model test, item-spefific Wald test,
Martin-Loef test, nonparametric Monte-Carlo tests,
itemfit and personfit statistics, various ICC plots. An eRm platform is provided at
http://r-forge.r-project.org/projects/erm/.Details
ll{
Package: eRm
Type: Package
Version: 0.15-4
Date: 2014-01-27
License: GPL-2
}
The basic input units for the functions are the person-item matrix X and the design matrix W.
Missing values in X are coded with NA.
By default, W is generated automatically, but it can be specified by the user as well.
The function call of the basic models can be achieved through RM(X, W),
RSM(X, W), and PCM(X, W).
The linear extensions provide the possibility to fit a more restricted model than its basic complement,
such as LLTM(X, W), LRSM(X, W),LPCM(X, W), but
also a generalization by imposing repeated measurement designs and group contrasts. These models can
be estimated by using, e.g.,
LLTM(X, W, mpoints = 2, groupvec = g),
LRSM(X, W, mpoints = 2, groupvec = g),
LPCM(X, W, mpoints = 2, groupvec = g),
and as very flexible multidimensional model for repeated measurements
LLRA(X, W, mpoints = 2, groups = G),
mpoints specifies the number of measurement or time points,
g is a vector with the group membership for each subject,
ordered according to the rows of the data matrix, and
G is a matrix with subject covariates (e.g., treatments),
RM produces an object belonging to the classes dRm, Rm, and
eRm. PCM and RSM produce objects belonging to the classes
Rm and eRm, whereas results of LLTM, LRSM, LLTM
and LLRA are objects of class eRm. For a detailled overview of all
classes defined in the package and the functions depending on them see the package's vignette.
We acknowledge Julian Gilbey for writing the plotPWmap function, Kathrin Gruber
for the function plotDIF, and Thomas Rusch for LLRA, related utilities and
functionality to calculate and plot item and test information.
The eRm package contains functions from the packages sna, gtools and ROCR.
Thanks to Carter T. Butts, Gregory R. Warnes, and Tobias Sing et al.References
Fischer, G. H., and Molenaar, I. (1995). Rasch Models - Foundations,
Recent Developements, and Applications. Springer.
Mair, P., and Hatzinger, R. (2007). Extended Rasch modeling: The eRm package for
the application of IRT models in R. Journal of Statistical Software, 20(9), 1-20.
Mair, P., and Hatzinger, R. (2007). CML based estimation of extended Rasch models
with the eRm package in R. Psychology Science, 49, 26-43.