Biostatistics Dept Seminar: Leveraging Bayesian mixture models to identify high-dimensional exposure patterns in heterogeneous populations

Biostatistics Department Seminar 

Title: Leveraging Bayesian mixture models to identify high-dimensional exposure patterns in heterogeneous populations

Abstract: Mixture models have found great utility to uncover patterns in large, heterogeneous study populations. However, majority subgroups within that population can, at times, overpower the direction and characterization of these patterns, leaving information of smaller-sized subgroups overlooked and ignored. This is commonly seen in a population such as the United States (US) where different backgrounds and subpopulations coexist. Unfortunately, much of the research which motivates US policy and decision making is driven by data accommodating the majority subgroup in the population. This ‘one-size-fits-all’ approach can be problematic if interventions and policy decisions are based on study results that are not representative of the entire population it intends to serve. This talk will discuss how we can leverage extensions of the standard mixture model framework to uncover exposure patterns from high-dimensional data within and across subpopulations that are typically overshadowed in population-based research. 

Speaker

Briana Stephenson is an assistant professor of Biostatistics at the Harvard T.H. Chan School of Public Health

Zoom Registration

If you would like to join via Zoom, please register here.

2024-2025 Monday Seminar Series

All seminars are held at 12:05 PM via Zoom and onsite. View all seminar information here.