Sensitivity analysis and choosing between alternative polytomous IRT models using Bayesian model comparison criteria. Issue 2 (7th February 2019)

• Record Type: Journal Article
• Authors: da Silva, Marcelo A.; Bazán, Jorge L.; Huggins-Manley, Anne Corinne
• Is Part Of: Communications in statistics. Volume 48:Issue 2(2019)
• Page Start: 601
• Page End: 620
• Publication Date: 2019-02-07
• Subjects: Generalized partial credit model -- Graded response model -- Item response theory -- Model comparison criteria -- No-u-turn hamiltonian monte carlo -- Prior sensitivity analysis; 47N30 (Applications in probability theory and statistics) -- 62F15 (Bayesian inference); Mathematical statistics -- Periodicals; Mathematical statistics -- Data processing -- Periodicals; Digital computer simulation -- Periodicals; 519.5
• DOI: 10.1080/03610918.2017.1390126
• Languages: English
• ISSNs: 0361-0918

Abstract

ABSTRACT: Polytomous Item Response Theory (IRT) models are used by specialists to score assessments and questionnaires that have items with multiple response categories. In this article, we study the performance of five model comparison criteria for comparing fit of the graded response and generalized partial credit models using the same dataset when the choice between the two is unclear. Simulation study is conducted to analyze the sensitivity of priors and compare the performance of the criteria using the No-U-Turn Sampler algorithm, under a Bayesian approach. The results were used to select a model for an application in mental health data.