Bayesian Model-Checking Methods for Cognitive Diagnostic Models

• In Event: Poster Session 4
  In Poster Session: Assessing Cognitive Ability and Processes

Abstract

Recently, there are two new methods that have been proposed as alternatives to the PP model checking method. They are referred as prior-predictive posterior posterior simulation method of Dey et al. (1998) and the pivotal discrepancy measure method of Johnson (2007). It is very interesting to check that if these two new methods are effective in detecting person misfit and overall goodness-of-fit in CMDs. Two simulation studies will be carried out in this study. The first simulation assesses the effectiveness of these two methods in detecting four different types of person misfit by incorporating the several person-fit measures. The second simulation is carried out to assess their effectiveness in detecting the local assumption of CDMs by incorporating the testlet effect.

Authors

• Nan Wang, Florida State University

• Russell Almond, Florida State University