Biostatistics 3:101-118 (2002)
© 2002 Oxford University Press
Flexible hazard regression modeling for medical cost data
Department of Biostatistics, University of Michigan, Ann Arbor, MI 48109-2029, USA. arvindj{at}umich.edu
Department of Biometrics, Cornell University, Ithaca NY 14853, USA
The modeling of lifetime (i.e. cumulative) medical cost data in the presence of censored follow-up is complicated by induced informative censoring, rendering standard survival analysis tools invalid. With few exceptions, recently proposed nonparametric estimators for such data do not extend easily to handle covariate information. We propose to model the hazard function for lifetime cost endpoints using an adaptation of the HARE methodology (Kooperberg, Stone, and Truong, Journal of the American Statistical Association, 1995, 90, 78–94). Linear splines and their tensor products are used to adaptively build a model that incorporates covariates and covariate-by-cost interactions without restrictive parametric assumptions. The informative censoring problem is handled using inverse probability of censoring weighted estimating equations. The proposed method is illustrated using simulation and also with data on the cost of dialysis for patients with end-stage renal disease.
Keywords: Cost-benefit analysis; Economic evaluation; Informative censoring; Quality of life; Survival analysis