Semiparametric likelihood estimation in the Clayton-Oakes failure time model

Multivariate failure time data arise when the sample consists of clusters a nd each cluster contains several possibly dependent failure times, The Clay ton-Oakes model (Clayton, 1978; Oakes, 1982) for multivariate failure times characterizes the intracluster dependence parametrically but allows arbitr ary specification of the marginal distributions. In this paper, we discuss estimation in the Clayton-Oakcs model when the marginal distributions are m odeled to follow the Cox (1972) proportional hazards regression model. Para meter estimation is based on an approximate generalized maximum likelihood estimator. We illustrate the model's application with example datasets.