Managing Uncertainty in Complex Stochastic

In this paper we present a novel method for emulating a stochastic, or 5 random output, computer model and show its application to a complex rabies 6 model. The method is evaluated both in terms of accuracy and computa7 tional eciency on synthetic data and the rabies model. We address the issue 8 of experimental design and provide empirical evidence on the eectiveness of 9 utilizing replicate model evaluations compared to a space-lling design. We 10 employ the Mahalanobis error measure to validate the heteroscedastic Gaus11 sian process based emulator predictions for both the mean and (co)variance. 12 The emulator allows ecient screening to identify important model inputs 13 and better understanding of the complex behaviour of the rabies model. 14