Multilevel Models of Intersectional Inequities-Introducing MAIHDA and Reimagining Multilevel Methods

This session is part of the ESRC Centre for Society and Mental Health's Research Methods Primer and Provocation series.

Intersectional MAIHDA (multilevel analysis of individual heterogeneity and discriminatory accuracy) is a new quantitative method for estimating inequalities in an intersectional framework. MAIHDA has many practical, methodological, and theory-oriented advantages over conventional approaches, such as single-level regression models with interaction terms. Proposed first in 2015 in social epidemiology, MAIHDA was soon hailed as the “new gold standard for investigating health disparities.” Today, it is being rapidly adopted across the health and social sciences.

At its heart, MAIHDA is a reimagining of multilevel (hierarchical) models for a new purpose: quantitative intersectional analysis. In this session, Professor Clare R. Evans introduces intersectional MAIHDA in an accessible way for scholars with varying backgrounds and familiarity with intersectionality and multilevel models. We explore examples to showcase MAIHDA’s potential, and discuss key practical issues to help get you started in thinking about applications in your own work.

About the presenter

Clare R. Evans is an Associate Professor in the Department of Sociology at the University of Oregon, where she serves as Core Faculty for the UO Center for Global Health and on the executive leadership teams for the UO programs in Global Health and Disability Studies. She received her ScD in Social and Behavioral Sciences at the Harvard T.H. Chan School of Public Health in 2015, and an MPH in Sociomedical Sciences at the Columbia University Mailman School of Public Health in 2011.

A social epidemiologist, medical sociologist, and quantitative methodologist, her research focuses on the intersectional social determinants of population health inequalities. In 2015, Dr. Evans proposed using hierarchical multilevel models to evaluate intersectional health inequalities—an approach now known as intersectional MAIHDA. Recently, she proposed and developed further extensions of the approach, including multicategorical MAIHDA for use in the clinical and biomedical sciences, random slopes MAIHDA for complex study and analytic designs, and eco-intersectional multilevel (EIM) modeling for investigation of environmental health injustices.