Estimating Lifetime or Episode-of-Illness Costs Under Censoring

• Activity Number: 230
• Type: Topic Contributed
• Date/Time: Monday, August 2, 2010 : 2:00 PM to 3:50 PM
• Sponsor: Health Policy Statistics Section
• Author(s): Anirban Basu*+ and Willard G. Manning
• Companies: The University of Chicago and The University of Chicago
• Keywords: Censored costs ; inverse probability weighting ; episode of illness ; survival versus intensity effects

Abstract

Health care costs data often encounter right censoring of cases before death or the end of the episode of illness. Concerns exist about the robustness of estimators based on inverse probability weighting (IPW) with the survival from censoring probabilities and their failure to distinguish between the effects of covariates on survival and intensity of utilization. We propose a new estimator that extends the class of two-part models to deal with random right censoring, more fully incorporates the information from the censored periods, and separates the survival effects from the intensity effects. Simulations show that IPW estimator is usually inefficient and sometime biased when censoring is large & covariates affect survival. We find our estimator to be unbiased and also more efficient for these designs. We apply these methods to data from the Medicare-SEER files on prostate cancer.