STANDARDIZED RATES OF RECURRENT OUTCOMES

Longitudinal studies are often concerned with estimating the rate of a n event that may recur. Examples are nonmelanoma skin cancer rates, sc reening rates for breast cancer using mammography and hospital admissi on rates. We propose simple estimators for directly and indirectly sta ndardized summary rates and relative rates of recurrent events and the ir variances. We also develop an estimator of the excess rate in an ar ea if the rate in another area applied. For non-recurrent events, the estimators are identical to the usual standardized summary rates.(5) T he estimators are independent of the underlying distribution of the ev ent of interest and allow for unequal follow-up times and event rate h eterogeneity among individuals. The method is not computationally inte nsive and does not require specialized software. We illustrate the app lication of the method in a retrospective cohort study of hospital uti lization patterns of Medicare enrollees in Boston and New Haven over a three and a half year period.