The purpose of this proposal is to develop statistical methods which are highly relevant to the study of the natural history of AIDS, markers of disease progression, and clinical trials in AIDS. Three projects are described: (a) The use of multiple imputation techniques to estimate the incubation period of AIDS. This is applicable to data in cohort studies in which the date of infection and date of AIDS diagnosis are frequently missing. (b) The use of Bayesian schemes to ac- count for the numerous sources of uncertainty in models of the growth of the AIDS epidemic. (c) The use of multivariate models for time-varying continuous markers of disease progression.
Showing the most recent 10 out of 23 publications