The importance of health in promoting economic development has been forcefully stated by the World Health Organization’s Commission on Macroeconomics and Health. In this paper, we look at the impact of own household health expenses on malaria incidence and ultimately on agricultural efficiency. We use a non-parametric method to estimate agricultural efficiency, therefore avoiding the issue of identification of the proper household agricultural production function. In addition the simar-wilson approach followed in this paper accounts for bias induced by serial correlation among farmers. A Tobit model with endogenous health production function is used to estimate the impact of malaria incidence on agricultural efficiency. Data come from the 2006 National Ugandan Household Survey. Estimation results suggest that marginal increase in the index of malaria incidence is expected to reduce agricultural efficiency by 0.07; in other words, ten percent increase in malaria incidence will decrease efficiency by 1.5 percent. We also found evidence of female farmers being more efficiency than male by 39.5 percent. Moreover, farmers who have been visited at least once by an extension agent appear more efficiency by 13.9 percent than those who were not.