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 (e.g., classroom, child development center), and/or near one another in space, time or jointly in space time. 

Pavel Chernyavskiy, assistant professor in the Department of Health Sciences at the University of Virginia, outlines several projects rooted in education and public health that feature correlated data, the methodological hurdles and triumphs therein.