General bootstrap for dual phi-divergence estimates

Abstract

A general notion of bootstrapped $\varphi$-divergence estimates constructed by exchangeably weighting sample is introduced. Asymptotic properties of these generalized bootstrapped $\varphi$-divergence estimates are obtained, by mean of the empirical process theory, which are applied to construct the bootstrap confidence set with asymptotically correct coverage probability. Some of practical problems are discussed, including in particular, the choice of escort parameter and several examples of divergences are investigated. Simulation results are provided to illustrate the finite sample performance of the proposed estimators.

References in corpus (5)

• Bootstrap consistency for general semiparametric $M$-estimation
• Generalized bootstrap for estimating equations
• Minimization of divergences on sets of signed measures
• Several Applications of Divergence Criteria in Continuous Families
• A new test procedure of independence in copula models via chi-square-divergence