Abstract
We present a novel inference approach which we call Sample Out-of-Sample (or SOS) inference. Our motivation is to propose a method which is well suited for data-driven stress testing, in which emphasis is placed on measuring the impact of (plausible) out-of-sample scenarios on a given performance measure of interest (such as a financial loss). The methodology is inspired by Empirical Likelihood (EL), but we optimize the empirical Wasserstein distance (instead of the empirical likelihood) induced by observations. From a methodological standpoint, our analysis of the asymptotic behavior of the induced Wasserstein-distance profile function shows dramatic qualitative differences relative to EL. For instance, in contrast to EL, which typically yields chi-squared weak convergence limits, our asymptotic distributions are often not chi-squared. Also, the rates of convergence that we obtain have some dependence on the dimension in a non-trivial way but which remains controlled as the dimension increases.

This publication has 23 references indexed in Scilit: