Variational Estimation for Multidimensional Generalized Partial Credit Model

Area of Science:

• Psychometrics
• Statistical modeling

Background:

• Multidimensional item response theory (MIRT) models are increasingly important in psychometrics.
• Existing efficient algorithms primarily focus on dichotomous MIRT models, leaving a gap for polytomous models.

Purpose of the Study:

• To develop an efficient and robust algorithm for estimating multidimensional generalized partial credit models.
• To address the limited attention given to polytomous MIRT model estimation algorithms.

Main Methods:

• A novel Gaussian variational estimation algorithm was developed.
• The algorithm was tested using simulation studies and real data analyses.

Main Results:

• The proposed Gaussian variational estimation algorithm demonstrated fast and accurate performance.
• The algorithm proved effective for the multidimensional generalized partial credit model.

Conclusions:

• The developed algorithm offers an efficient and robust solution for estimating polytomous MIRT models.
• This work advances psychometric methodology for complex response data.