Sensitivity analysis and performance extrapolation for computer simulation models

The paper presents a method for deriving sensitivities of performance measures for computer simulation models. It shows that both the sensitivities (derivatives, gradients, Hessians, etc.) and the performance measure can be estimated simultaneously from the same simulation. The present method is based on probability measure transformations derived from the efficient score. The paper also presents a rather general procedure from which perturbation analysis and the present method can be viewed as particular cases. Applications to reliability models and stochastic shortest path networks are given.