General Departmental Seminar Series
Semiparametric Estimation in the
Gamma Frailty Model with Dependent Censoring
Hongyu Jiang, Department of Statistics
University of Wisconsin-Madison
Friday, December 10, 1999, 12:00-1:00 p.m.
E5/584 Clinical Science Center, 600 Highland Avenue
We consider a variation of th ecompeting risks problem in which a terminal event censors a non-terminal event, but not vice versa. The joint distribution of the events is formulated via the Clayton (1978) model, with the marginal distributions unspecified. An estimator for the association parameter is obtained by extending Oakes' concordance estimating equation. A goodness-of-fit test is developed for checking the adequacy of the model. Two methods of estimation for the marginal distributions will be presented. Simulations demonstrate that the methods work well with practical sample sizes. An application to data on morbidity and mortality in leukemia patients will illustrate the proposals.
Back to General Departmental Seminar Series