The Statistical Methods for Health Equity Series is a monthly online series co-hosted by the Data Science for Health Equity community and the Department of Statistical Science at University College London.

We are excited to announce the next instalment of our webinar series with speaker Prof. J. Sunil Rao, Director of Biostatistics & Co-Associate Director, Cancer Data Sciences, University of Minnesota.

Title:  Distorted Variable Analysis

Abstract:  We introduce Distorted Variable Analysis (DVA), a tree-based methodological framework designed to identify, quantify and provide strategies to reduce disparities based on observational data. 

DVA uses a tree-based partitioning approach to identify subgroups with differential outcome distributions with respect to a focus variable.  Under certain assumptions, strategies for disparity reduction emerge by manipulation of modifiable risk factors resulting in a redistribution of individuals to different partitions using a second stage classified mixed model prediction (CMMP) framework.  Empirical validation on synthetic and electronic health record (EHR) data confirm DVA's ability to identify actionable pathways for disparity reduction.  This is joint work with Henge Ke of the Amgen Corporation and Claudio Conversano of the University of Cagliari, Italy.  

J. Sunil Rao, Ph.D. is Professor of Biostatistics and Health Data Science at the University of Minnesota, Twin Cities.  He is also co-Associate Director of AI and Cancer Data Science and the Director of Biostatistics at the Masonic Cancer Center.  He is a Fellow of the American Statistical Association (ASA), the Institute of Mathematical Statistics (IMS) and Elected Member of the International Statistical Institute (ISI).  

His areas of research interest are primarily focused on cancer research these days and span the full continuum from the basic sciences (transcriptomic, epigenetic, proteomic research) to the population sciences (cancer epidemiology, small area estimation, health disparity research).  He has published over 115 peer-reviewed publications and two important books (Statistical Methods in Health Disparity Research in 2023 and Robust Small Area Estimation (with Jiming Jiang) in 2025 - both published by CRC Press).

Please direct any questions about the webinar series to info@datascienceforhealthequity.com.