Conditional Categorical Response Models with Application to Treatment of Acute Myocardial Infarction

For a sample of 2361 patients admitted with suspected acute myocardial in-farction (AMI) to a set of 37 hospitals, recorded patient response variables include eligibility for treatment with aspirin, eligiblilty for treatment with thrombolytics, treatment with aspirin received, treatment with thrombolytics received, and short-term patient survival. Each of these ve variables has two levels resulting in a 2 5 contingency table. Covariate information includes age, sex, race and comorbidity status. Because the responses arrive in sequence we model this data in three stages: eligibility, then treatment received given eligibility and nally short-term survival given eligibility and treatment received, all given the covariates. Issues of interest include extent to which treatment received matches eligibility, whether probability of survival is aaected by treatment status and how the chance of mortality is aaected by whether or not treatment received matches eligibility. Innuence of co-variate information on these quantities is examined. These quantities are studied at the hospital level adjusted for case mix and also in aggregate, marginalizing over hospitals. .