Resampling Fewer Than n Observations: Gains, Losses, and Remedies for Losses

Resampling Fewer Than n Observations: Gains, Losses, and Remedies for Losses

Report Number
419
Authors
Leo Breiman
Citation
Journal of Time Series Analysis, Vol.17
Abstract

We discuss a number of resampling schemes in which $m=o(n)$ observations are resampled. We review nonparametric bootstrap failure and give results old and new on how the $m$ out of $n$ with replacement bootstraps and without replacement works. We extend work of Bickel and Yahav (1988) to show that $m$ out of $n$ bootstraps can be made second order correct, if the usual nonparametric bootstrap is correct and study how these extrapolation techniques work when the nonparametric bootstrap doesn't.

PDF File
Postscript File