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.