Robust simulation-based estimation

The simulation-based inferential method called indirect inference was originally proposed for statistical models whose likelihood is difficult or even impossible to compute and/or to maximize. In this paper, indirect estimation is proposed as a device to robustify the estimation for models where this is not possible or difficult with classical techniques such as M-estimators. We derive the influence function of the indirect estimator, and present results about its gross-error sensitivity and asymptotic variance. Two examples from time series are used for illustration.