Multiple Imputation for Missing Data Analysis in Proportional Odds Models for Ordinal Response Variables

• In Event: Adaptations of GLM for Advanced Data Analysis

Abstract

Although multiple imputation (MI) for dealing with missing data has been getting popularity in educational research, previous research mainly focuses on normally distributed continuous variables. There is a great need to impute ordinal categorical variables. Further, since different methods can be performed for MI, it is unclear which one should be recommended for empirical use. The purpose of this study is to illustrate the use of both MI for a single ordinal variable and multiple imputation by chained equations (MICE) for multivariate variables in ordinal logistic regression to predict mathematics proficiency levels. In addition, it compares the results of the PO models with and without imputation and compares the results of the models with different numbers of imputations.

Authors

• Xing Liu, Eastern Connecticut State University

• Haiyan Bai, University of Central Florida

• Hari P. Koirala, Eastern Connecticut State University