Asymptotic Refinements of a Misspecification-Robust Bootstrap for Empirical Likelihood Estimators

I propose a nonparametric iid bootstrap procedure for the empirical likelihood (EL), the exponential tilting (ET), and the exponentially tilted empirical likelihood (ETEL) estimators. The proposed bootstrap achieves sharp asymptotic refinements for t tests and confidence intervals based on such estimators. Furthermore, my bootstrap is robust to possible model misspecification, i.e., it achieves asymptotic refinements regardless of whether the assumed moment condition model is correctly specified or not. This result is new, because asymptotic refinements of the bootstrap for EL estimators have not been established in the literature even under correct model specification. Monte Carlo simulation results are provided.