Research
Pacific Metrics’ Research staff collectively has many years of applied experience with a wide variety of models for test data, including, but not limited to, the following item-response theory models.
Models for scores in two categories (e.g., right/wrong)
Lord’s 3-parameter model (3-PL)
Birnbaum’s 2-parameter model (2-PL)
Rasch model (1-PL)
Models for scores in more than two ordered categories:
Muraki’s Generalized Partial Credit model (GPCM)
Master’s Rating Scale Model (RSM)
Andrich’s Partial Credit Model (PCM)
Samajima’s Graded Response Model (GRM)
The computer programs used in conjunction with these models include industry standards such as PARSCALE, Bilog, Winsteps, and Facets.