A Likelihood Approach to Item Response Theory Equating of Multiple Forms.

Area of Science:

• Psychometrics
• Statistical Modeling

Background:

• Test equating is crucial for score comparability across different test forms.
• Current methods often have limitations in handling complex item parameter relationships.

Purpose of the Study:

• To propose a novel, likelihood-based method for simultaneous test equating of numerous forms.
• To address heteroskedasticity and correlation in item parameter estimates.

Main Methods:

• Utilizing an Item Response Theory (IRT) framework.
• Implementing a novel likelihood-based procedure for simultaneous item parameter linking.
• Accounting for heteroskedasticity and correlations among item parameter estimates.

Main Results:

• Simulation studies demonstrate superior efficiency of the proposed equating coefficient estimates.
• The new method offers improved accuracy compared to existing techniques.

Conclusions:

• The proposed IRT-based method provides a more efficient approach to test equating.
• This advancement enhances score comparability and reliability in large-scale assessments.