BibTex format
@article{Young:2003,
author = {Young, GA},
journal = {Metron},
pages = {227--242},
title = {Better bootstrapping by constrained prepivoting},
volume = {61},
year = {2003}
}
Publications
Citation
RIS format (EndNote, RefMan)
TY - JOUR
AB - Bootstrap methods are attractive empirical procedures for assessment of errors in problems of statistical estimation, and allow highly accurate inference in a vast range of problems. Conventional bootstrapping involves sampling from the empirical distribution function in nonparametric problems, or a fitted parametric model in parametric inference. Recently, much attention has been focussed on methods for reduction of the error properties of bootstrap procedures, by systematic modification of the sampling model, in a way that is dependent on the parameter of interest. In this paper, we provide a general perspective on the bootstrap, based on the notion of prepivoting, with the specific aim of synthesizing recent developments related to modified, or "weighted", bootstrap procedures, and provide a critical evaluation of the practical benefits of such procedures over conventional bootstrap schemes and alternative analytic methods.
AU - Young,GA
EP - 242
PY - 2003///
SN - 0026-1424
SP - 227
TI - Better bootstrapping by constrained prepivoting
T2 - Metron
VL - 61
ER -