[R-pkgs] package ltm -- version 0.8-0
dimitris.rizopoulos at med.kuleuven.be
Tue May 8 10:54:09 CEST 2007
I'd like to announce the release of the new version of package `ltm'
(i.e., ltm_0.8-0 soon available from CRAN) for Item Response Theory
analyses. This package provides a flexible framework for analyzing
dichotomous and polytomous data under IRT, including the Rasch model,
the Two-Parameter Logistic model, Birnbaum's Three-Parameter model,
the Latent Trait model with up to two latent variables (allowing also
for nonlinear terms), and Samejima's Graded Response model.
Furthermore, supporting functions for descriptive statistics,
goodness-of-fit, ability estimation and plotting are available.
New features include:
* The new functions person.fit() and item.fit() compute p-values for
person- and item-fit statistics for IRT models for dichotomous data.
The `simulate.p.value' argument enables the computation of p-values
based on a Monte Carlo procedure.
* The new function unidimTest() checks the unidimensionality
assumption for dichotomous data IRT models, using a Modified Parallel
* The new function testEquatingData() prepares data-sets for test
equating by common items. In particular, two types of common item
equating are included: alternate form equating (where common and
unique items are analyzed simultaneously) and across sample equating
(where different sets of unique items are analyzed separately based on
previously calibrated anchor items).
* grm() now works with the available cases when incomplete data
(i.e., in the presence of NAs) are analyzed.
* better algorithms, for Missing At Random missing data mechanisms,
have been written for grm(), ltm(), rasch() and tpm().
* a residuals() method has been added for `grm', `ltm', `rasch', and
`tpm' objects that computes Pearson-type residuals.
* factor.scores() and fitted() methods for classes `grm', `ltm',
`rasch', and `tpm' allow now for NAs in the `resp.patterns' argument,
enabling thus the computation of ability estimates and fitted values
for incomplete response patterns.
* the fitted() method now allows also for the computation of
marginal and conditional (on the latent variable(s)) probabilities;
this feature is controlled by the new `type' argument.
* for more details and other news, check the CHANGES file that ships
with the package.
More information as well as .R files illustrating the capabilities of
the package can be found in the Rwiki page of `ltm' available at:
Future plans include the development of functions for fitting Bock's
Nominal Response model and the option for Differential Item
I'd like also to thank all users of `ltm' for providing valuable
feedback, and welcome any additional feedback (questions, suggestions,
More information about the R-packages