My major research interests are in the area of survival analysis, especially models for the effect of explanatory variables on survival and for multivariate survival data. Early contributions included investigation of the efficiency of Cox’s partial likelihood as compared with fully parametric models, development of approximate likelihood procedures for censored data and an extension of Kendall’s tau statistic for testing independence for bivariate data subject to censoring in both components. More recent work has largely focused on the models for bivariate survival models generated by unobserved random effects, often called frailties. There are close connections with so-called “Archimedean copula” models for bivariate data.
