The use of random effects assumes that every region has some common risk rates and allows estimates to combine information from several regions. This random effect is common in Bayesian approach disease mapping using lognormal model. Bayesian posterior distributions are obtained via Markov Chain Monte Carlo (MCMC) computations. HIV Data was obtained from National Institute for Research in Tuberculosis. The result of the study reveals that the random effects model, gives the smoother values of relative risk than the Poisson gamma model. Spatial analysis is proved to be more useful for studying spread of HIV analysis.