A Conditional Joint Modeling Approach for Compensatory Multidimensional Item Response Model and Response Times

• In Event: Marriott Roundtable Session 29
  In Roundtable Session: Estimation and Reporting of Multidimensional Item Response Theory Models

Abstract

Many modeling methods have been proposed to incorporate response times into the speed-accuracy analysis in order to discuss the within-person relationship between the latent speediness and cognitive abilities. In this research, a new conditional joint modeling approach is proposed that allows reflecting the structural relationship between the multi-cognitive dimensions and the working speed of test-takers. The structural relationship between the working speed and accuracy based on the measure of multidimensional abilities could be manifested by joint modeling the variance-covariance structures on both item and person side. This modeling approach is an extension of the hierarchical modeling framework proposed by van der Linden (2007). The feasibility of this modeling approach is investigated vis-à-vis a Monte Carlo simulation.

Authors

• Kaiwen Man, University of Alabama

• Hong Jiao, University of Maryland-College Park

• Peida Zhan, Beijing Normal University