A multilevel survival frailty model is presented for analyzing clustered and recurrent urinary tract infections among elderly women residing in aged-care institutions. At the subject level, serial dependence is expected between recurrent events recorded on the same individual. At the cluster level, correlations of observations within the same institution are present due to the inherent residential environment and hierarchical setting. Two random components are therefore incorporated explicitly within the survival frailty model to account for the simultaneous heterogeneity and autoregressive structure. A Splus computer program is developed for the estimation of fixed effect and variance component parameters.