Upcoming Developments

After a hiatus, development on OSCATS is continuing.  Below are listed some changes to appear in the Hg repository soon, and the next release is planned for 1-2 months from now.

  Also, there are some new (and rather experimental) introspection-based MATLAB bindings for GObject at the gmatlab project.  They're ready for general use, but those interested who have some stamina may want to take a look.

• GObject-Introspection support for liboscats
• Shift language bindings to GO-I methods (perl, python, java)
• Unified latent space object for continuous and discrete latent variables
• Unified model support, allowing each Administrand to have an arbitrary number of models (for different purposes, e.g. simulation, estimation, calibration, statistical interest)
• Support sub-classing models and algorithms in bound languages
• More common IRT/CD models
• More item selection algorithms, including a-Stratified and Dual-purpose methods
• Simpson-Hetter exposure control

OSCATS 0.5 Released

OSCATS version 0.5 has been released.  Source and compiled Windows binary distributions are available, as well as a compiled distribution of GSL 1.14 for Windows.

Note of Upcoming Changes:
The language bindings will be shifting to GObject Introspection-based implementations, where possible, by version 1.0.  This will streamline bindings generation even more and make OSCATS potentially available in more programming languages.  However, it may entail some changes to function nomenclature.

Welcome to OSCATS!

A working preliminary version of OSCATS has been loaded into the code repository.  Source and Windows binary distributions for version 0.5 will be available shortly (waiting to correct a problem with the Java bindings on Windows).

This initial version includes bindings for Python, Perl, PHP, and Java for use of built-in functions, models, and algorithms.  OSCATS can be used from Matlab via the Java bindings.  Full bindings for Matlab, as well as support for creating new models and algorithms in bound languages is targeted for version 1.0.

Features:

• IRT Models included: 1PL (Rasch), 2PL, 3PL, Nominal response
• Classification Models included: DINA, NIDA
• Selection Algorithms included:
• Random
• Optimize an arbitrary criterion
• Closest difficulty
• Maximize Fisher information
• Maximize KL information (for IRT or classification)
• Can simulate based on either IRT or classification
• Support for examinee covariates in IRT models
• Support for tagging item characteristics (e.g. "algebra," "geometry," "negative stem," etc.)