Gautam Gowrisankaran, Associate Fellow
Robert J. Town, Co-Principal Investigator

Bayesian Inference for Hospital Quality in a Selection Model

This project develops new economic methods to infer hospital quality in a model with discrete dependent variables and non-random selection. Mortality rates in patient discharge records are widely used to infer hospital quality. However, hospital admission is not random and some hospitals may attract patients with greater unobserved severity of illness than others. In this situation, the assumption of random admission leads to spurious inference about hospital quality. This study controls for hospital selection using a model in which distance between the patient’s residence and alternative hospitals are key exogenous variables. Bayesian inference in this model is feasible but very computationally intensive using a Markov chain Monte Carlo posterior simulator. Results to date use data on 74,848 Medicare patients admitted to 114 hospitals in Los Angeles County from 1989 through 1992 with a diagnosis of pneumonia. They find the smallest and largest hospitals to be of high quality and public hospitals to be of low quality. There is strong evidence of dependence between the unobserved severity of illness and the assignment of patients to hospitals. Consequently, a conventional probit model leads to inference about quality markedly different than those in this study’s selection model. The researchers are now analyzing preliminary results on heart bypass patients from throughout the state of California.