Multilevel modeling of spatially nested functional data: spatial variation in hospitalization rates among U.S. dialysis patients

Utilizing data from the United States Renal Data System (USRDS), we propose a novel multilevel spatiotemporal functional model to study spatiotemporal patterns of hospitalization rates among dialysis facilities in the U.S. Hospitalization rates of dialysis facilities are considered as spatially nested functional data with longitudinal hospitalizations nested in dialysis facilities and dialysis facilities nested in geographic regions. The proposed modeling is applied to analyze data from USRDS for mapping spatiotemporal patterns of hospitalization rates for over 700 health service areas (HSA) across U.S.

SPEAKER: Damla Senturk, PhD, Professor, Department of Biostatistics, University of California, Los Angeles