Comparing the Efficacy of Fixed Effect and MAIHDA (Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy) Models in Predicting Outcomes for Intersectional Social Identity Groups

• In Event: AERA Roundtable Session Saturday 9:50 am Four Seasons Ballroom 1
  In Roundtable Session: Innovative Approaches to Quantitative Analysis: Addressing Bias, Model Constraints, and Intersectionality in Social Research (Table 3)

Abstract

This investigation examines the efficacy of multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA) over fixed effect models when performing intersectional studies. The research questions are: 1) What are typical strata representation rates and outcomes on physics research-based assessments? 2) To what extent do MAIHDA models create more accurate predicted strata outcomes than fixed effects models? 3) To what extent do MAIHDA models allow the modeling of smaller strata sample sizes? We simulated 3,000 datasets based on real-world data. MAIHDA created more accurate and precise predictions than fixed effect models. We also found that using MAIHDA could allow researchers to disaggregate their data further, creating smaller group sample sizes while maintaining more accurate findings than fixed effect models.

Authors

• Ben Van Dusen, Iowa State University

• Heidi Cian, Maine Mathematics and Science Alliance

• Jayson Nissen, Montana State University

• Lucy Arellano, University of California - Santa Barbara