RUS  ENG
Full version
JOURNALS // Zapiski Nauchnykh Seminarov POMI // Archive

Zap. Nauchn. Sem. POMI, 2013 Volume 412, Pages 138–180 (Mi znsl5645)

This article is cited in 3 papers

Large Deviation Principle for moderate deviation probabilities of empirical bootstrap measure

M. S. Ermakovab

a St. Petersburg State University, St. Petersburg, Russia
b Mechanical Engineering Problems Institute of RAS, St. Petersburg, Russia

Abstract: We prove two LDPs (LDP) in the zone of moderate deviation probabilities. First we establish LDP for the conditional distributions of moderate deviations of empirical bootstrap measure given empirical probability measure. Second we establish LDP for the joint distribution of empirical measure and empirical bootstrap measure. Using these LDPs, on the base of contraction principle, we deduce similar LDPs for statistical functionals having the Hadamard derivatives. The LDPs for moderate deviations of empirical quantile processes and empirical bootstrap copula function are given as illustration of these results.

Key words and phrases: Large Deviation Principle, moderate deviations, bootstrap, empirical measure.

UDC: 519.2

Received: 12.11.2012


 English version:
Journal of Mathematical Sciences (New York), 2015, 204:1, 90–115

Bibliographic databases:


© Steklov Math. Inst. of RAS, 2024