Statistics Seminars: On assessing time dependence of association in bivariate current status data
24 January 2011 15:15 in CM221
In this talk, the temporal variation in the strength of association in bivariate current status data is studied. Several association measures and their methods of estimation are investigated with a view to assessing their performance for identifying age-dependent effects. A new measure of association relevant for shared frailty models for current status data is proposed. This novel measure, which is based on Clayton's copula, is particularly convenient owing to its connection with the relative frailty variance and its interpretability in suggesting appropriate frailty models. We introduce a method of estimation and standard errors for this measure. To improve the interpretability of the dependency pattern, various smoothing techniques are applied to capture trends with age. The methods are illustrated with bivariate serological survey data on different infections, where the age-varying association is likely to represent heterogeneities in activity levels and/or susceptibility to infection.
Host: Jochen Einbeck
Contact email@example.com for more information