Decision Consistency and Accuracy of Household Food Insecurity Classifications Using a Partial Credit Model

• In Event: Methodological Approaches in Rasch Measurement

Abstract

Household food insecurity is a condition that occurs when households lack access to the food they require for a healthy, active lifestyle. The U.S. Department of Agriculture (USDA) measures household food insecurity annually with the Household Food Security Survey Module (HFSSM), an 18-item survey that includes both dichotomous and polytomous items that reference food hardships for adults and children in the household. The HFSSM was originally calibrated and has been maintained with a dichotomous Rasch model (Engelhard, Rabbitt, & Engelhard, 2017). The purpose of this study is to explore issues of decision consistency and accuracy when modeling household food insecurity with a partial credit Rasch model. Implications of this work for policy and research are discussed.

Authors

• Victoria T. Tanaka, South Carolina Department of Education

• George Engelhard, University of Georgia

• Matthew Rabbitt, The United States Department of Agriculture Economic Research Service