|
Activity Number:
|
340
- SPEED: Bayesian Methods, Part 1
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 30, 2019 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
|
Abstract #306930
|
Presentation
|
|
Title:
|
A New Bayesian Person-Fit Analysis Method for Item Response Theory Models Using Pivotal Discrepancy Measures
|
|
Author(s):
|
Adam Combs*
|
|
Companies:
|
Robert Morris University
|
|
Keywords:
|
Bayesian;
Item Response Theory;
Person-fit;
Model Checking;
Posterior-Predictive;
MCMC
|
|
Abstract:
|
Evaluating person-fit in Bayesian Item Response Theory (IRT) models is typically done using the posterior-predictive (PP) method. In recent years, a new Bayesian model checking method based on pivotal discrepancy measures (PDMs) has been proposed for general Bayesian models. This method can be employed using standard MCMC output. We apply this new PDM method to person-fit checking in Bayesian IRT models using the popular Lz person-fit measure. Simulation studies are done to compare the PDM method with the PP method under a two-parameter normal ogive model (2PNO). Type I error rates and detection rates of some specific model violations are investigated. The main results show that the PDM method is less conservative and more powerful than the PP method under all simulation conditions.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2019 program
|
