We have developed REG-PERFIT in Matlab 2015a release compiled it as a user-friendly standalone application for Windows 64-bit operating systems. Users can decide whether to use the advanced Matlab version of REG-PERFIT, or the standalone version (which does not require any programming skills). We have tested the program in several computers with different versions of Windows (7/8/8.1) and found that it works correctly.
REG-PERFIT implements a general parametric IRT approach for identifying sources of misfit in response patterns that have been classified as potentially inconsistent by a global person fit index. The approach, which is based on the weighted least squared regression of the observed responses on the model-expected responses, can be used with a variety of unidimensional and multidimensional models intended for binary, graded, and continuous responses, and consists of procedures for identifying: (a) general deviation trends, (b) local inconsistencies, and (c) single response inconsistencies.