Title: Statistical modeling for heterogeneous populations with application to hospital admission prediction
Authors: Menggang Yu - University of Wisconsin - Madison (United States) [presenting]
Abstract: The motivation arises from risk modeling for large hospital and health care systems that provide services to diverse and complex patients. Modeling such heterogeneous populations poses many challenges. Often, heterogeneity across a population is determined by a set of factors such as chronic conditions. When these stratifying factors result in overlapping subpopulations, it is likely that the covariate effects for the overlapping groups have some similarity. We propose to exploit this similarity by imposing structural constraints on the importance of variables in predicting outcome such as hospital admission. We prove an oracle property for our estimation method that enables construction of confidence intervals. We also show that even when the structural assumptions are misspecified, our method will still include all of the truly nonzero variables in large samples and therefore provide valid asymptotic statistical inference. We demonstrate impressive performance of our method in extensive numerical studies and on an application in hospital admission prediction and validation for the Medicare population at the University of Wisconsin-Madison Health System.