Bayesian conditional-independence modeling of the AIDS epidemic in Englandand Wales

We describe the use of conditional-independence modeling, Bayesian inferenc e and Markov chain Monte Carlo, to model and project the HIV-AIDS epidemic in homosexual/bisexual males in England and Wales. Complexity in this analy sis arises through selectively missing data, indirectly observed underlying processes, and measurement error. Our emphasis is on presentation and disc ussion of the concepts, not on the technicalities of this analysis, which c an be found elsewhere [D. De Angelis, W.R. Gilks, N.E. Day, Bayesian projec tion of the the acquired immune deficiency syndrome epidemic (with discussi on), Applied Statistics, in press]. (C) 1999 Elsevier Science B.V. All righ ts reserved.