Evaluation of the Ability Estimates Under the Factor Mixture Model and Mixture IRT (Item Response Theory) Model

• In Event: Roundtable Session 67
  In Roundtable Session: Mixture and Growth Mixture Models

Abstract

Estimating respondents’ abilities or latent trait is a very important issue in testing and measurement contexts. To date, there has been little research investigating the accuracy of estimating individual abilities with changing conditions under Factor Mixture Models and Mixture IRT models. This study focuses on evaluation of the ability estimates under such models using a Monte Carlo simulation.

Authors

• Xiaodong Hou, University of Maryland - College Park

• Gregory R. Hancock, University of Maryland