Pavel Chernyavskiy, assistant professor in the Department of Health Sciences at the University of Virginia, led the spring presentation of the 2025-26 Methodology Applications Series April 24 at the Nebraska Union.
Video is now available of Chernyavskiy’s presentation, titled, “Everything is Important and Everything is Correlated: Challenges and Opportunities of Working in Correlated Data.”
Much of the data in social and biomedical sciences features non-ignorable correlations that must be considered in analysis. This correlation arises when multiple observations are taken on the same subject or cluster of subjects, and/or near one another in space, time or jointly in space time. Depending on the modeling goals, the analyst must make several consequential statistical choices that are often under-discussed.
Chernyavskiy’s presentation covered several projects rooted in education and public health that feature correlated data, the methodological hurdles and triumphs therein. He also discussed some opportunities to extend existing models, such as areal indices using spatial models; educational assessment data using Item Response Models; and displayed effect from automatic facial coding software.
The 2025-26 Methodology Applications Series was hosted by CYFS’ Nebraska Academy for Methodology, Analytics and Psychometrics with funding support from the Nebraska Research Initiative.
The series will resume in Fall 2026.