Spatio-temporal modeling of sparse geostatistical malaria sporozoite rate data using a zero inflated binomial model

► We develop Bayesian zero inflated binomial (ZIB) geostatistical models. ► Compared ZIB models with standard analogues to analyze sparse sporozoite data. ► Sporozoite rate vary over time and space. ► Bayesian ZIB models fit sparse data better than ordinary binomial models.