Space-time confounding adjusted determinants of child HIV/TB mortality for large zero-inflated data in rural South Africa

► Problem of Bayesian MCMC inversion of very large data in estimating the spatial random effects known as the “Big N”. ► Use of flexible exponential family link functions to exponential family predictors to avoid identifiability related problems. ► South Africa's HIV/TB burden in children and efficient modeling thereof. ► Addresses space-time confounding in multivariate analyses of very large data structures. ► Estimates useful for policy formulation and modeling which results in risk maps which are user friendly.