Bootstrap sample size in nonregular cases

Shao, Jun

doi:10.1090/S0002-9939-1994-1227529-8

Bootstrap sample size in nonregular cases
HTML articles powered by AMS MathViewer

by Jun Shao PDF

Proc. Amer. Math. Soc. 122 (1994), 1251-1262 Request permission

Abstract:

We study the bootstrap estimator of the sampling distribution of a given statistic in some nonregular cases where the given statistic is nonsmooth or not-so-smooth. It is found that the ordinary bootstrap, based on a bootstrap sample of the same size as the original data set, produces an inconsistent bootstrap estimator. On the other hand, when we draw a bootstrap sample of a smaller size with the ratio of the size of the bootstrap sample over the size of the original data set tending to zero, the resulting bootstrap estimator is consistent. Examples of these nonregular cases are given, including the cases of functions of means with null first-order derivatives, differentiable statistical functionals with null influence function, nondifferentiable functions of means, and estimators based on some test results.

References

Lavy Abramovitch and Kesar Singh, Edgeworth corrected pivotal statistics and the bootstrap, Ann. Statist. 13 (1985), no. 1, 116–132. MR 773156, DOI 10.1214/aos/1176346580
K. B. Athreya, Bootstrap of the mean in the infinite variance case, Ann. Statist. 15 (1987), no. 2, 724–731. MR 888436, DOI 10.1214/aos/1176350371
Gutti Jogesh Babu, Bootstrapping statistics with linear combinations of chi-squares as weak limit, Sankhyā Ser. A 46 (1984), no. 1, 85–93. MR 768919
Rudolf Beran, Prepivoting to reduce level error of confidence sets, Biometrika 74 (1987), no. 3, 457–468. MR 909351, DOI 10.1093/biomet/74.3.457
Peter J. Bickel and David A. Freedman, Some asymptotic theory for the bootstrap, Ann. Statist. 9 (1981), no. 6, 1196–1217. MR 630103
Paul Deheuvels, David M. Mason, and Galen R. Shorack, Some results on the influence of extremes on the bootstrap, Ann. Inst. H. Poincaré Probab. Statist. 29 (1993), no. 1, 83–103 (English, with English and French summaries). MR 1204519
B. Efron, Bootstrap methods: another look at the jackknife, Ann. Statist. 7 (1979), no. 1, 1–26. MR 515681
Bradley Efron, The jackknife, the bootstrap and other resampling plans, CBMS-NSF Regional Conference Series in Applied Mathematics, vol. 38, Society for Industrial and Applied Mathematics (SIAM), Philadelphia, Pa., 1982. MR 659849
Bradley Efron, Better bootstrap confidence intervals, J. Amer. Statist. Assoc. 82 (1987), no. 397, 171–200. With comments and a rejoinder by the author. MR 883345
Peter Hall, Theoretical comparison of bootstrap confidence intervals, Ann. Statist. 16 (1988), no. 3, 927–985. With a discussion and a reply by the author. MR 959185, DOI 10.1214/aos/1176350933
Peter Hall, On the relative performance of bootstrap and Edgeworth approximations of a distribution function, J. Multivariate Anal. 35 (1990), no. 1, 108–129. MR 1084945, DOI 10.1016/0047-259X(90)90019-E
Frank R. Hampel, The influence curve and its role in robust estimation, J. Amer. Statist. Assoc. 69 (1974), 383–393. MR 362657

Sample quantiles in some nonregular cases and the vulnerable bootstrap

Wei-Yin Loh, Estimating an endpoint of a distribution with resampling methods, Ann. Statist. 12 (1984), no. 4, 1543–1550. MR 760707, DOI 10.1214/aos/1176346811
Robert J. Serfling, Approximation theorems of mathematical statistics, Wiley Series in Probability and Mathematical Statistics, John Wiley & Sons, Inc., New York, 1980. MR 595165

Bootstrap variable selection in regression

Jan W. H. Swanepoel, A note on proving that the (modified) bootstrap works, Comm. Statist. A—Theory Methods 15 (1986), no. 11, 3193–3203. MR 860478, DOI 10.1080/03610928608829303