Document Type
Article
Language
eng
Publication Date
10-1-2017
Publisher
SAGE Publishing
Source Publication
Journal of Educational and Behavioral Statistics
Source ISSN
1076-9986
Abstract
Questionnaires that include items eliciting count responses are becoming increasingly common in psychology. This study proposes methodological techniques to overcome some of the challenges associated with analyzing multivariate item response data that exhibit zero inflation, maximum inflation, and heaping at preferred digits. The modeling framework combines approaches from three literatures: item response theory (IRT) models for multivariate count data, latent variable models for heaping and extreme responding, and mixture IRT models. Data from the Behavioral Risk Factor Surveillance System are used as a motivating example. Practical implications are discussed, and recommendations are provided for researchers who may wish to use count items on questionnaires.
Recommended Citation
Magnus, Brooke E. and Thissen, David M., "Item Response Modeling of Multivariate Count Data With Zero Inflation, Maximum Inflation, and Heaping" (2017). Psychology Faculty Research and Publications. 293.
https://epublications.marquette.edu/psych_fac/293
Comments
Accepted version. Journal of Educational and Behavioral Statistics, Vol. 42, No. 5 (October 1, 2017): 531-558. DOI. © 2017 SAGE Publications. Used with permission.