Inconsistency of bootstrap: The Grenander estimator
Sen, Bodhisattva ; Banerjee, Moulinath ; Woodroofe, Michael
Ann. Statist., Tome 38 (2010) no. 1, p. 1953-1977 / Harvested from Project Euclid
In this paper, we investigate the (in)-consistency of different bootstrap methods for constructing confidence intervals in the class of estimators that converge at rate n1/3. The Grenander estimator, the nonparametric maximum likelihood estimator of an unknown nonincreasing density function f on [0, ∞), is a prototypical example. We focus on this example and explore different approaches to constructing bootstrap confidence intervals for f(t0), where t0 ∈ (0, ∞) is an interior point. We find that the bootstrap estimate, when generating bootstrap samples from the empirical distribution function $\mathbb{F}_{n}$ or its least concave majorant F̃n, does not have any weak limit in probability. We provide a set of sufficient conditions for the consistency of any bootstrap method in this example and show that bootstrapping from a smoothed version of F̃n leads to strongly consistent estimators. The m out of n bootstrap method is also shown to be consistent while generating samples from $\mathbb{F}_{n}$ and F̃n.
Publié le : 2010-08-15
Classification:  Decreasing density,  empirical distribution function,  least concave majorant,  m out of n bootstrap,  nonparametric maximum likelihood estimate,  smoothed bootstrap,  62G09,  62G20,  62G07
@article{1278861239,
     author = {Sen, Bodhisattva and Banerjee, Moulinath and Woodroofe, Michael},
     title = {Inconsistency of bootstrap: The Grenander estimator},
     journal = {Ann. Statist.},
     volume = {38},
     number = {1},
     year = {2010},
     pages = { 1953-1977},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1278861239}
}
Sen, Bodhisattva; Banerjee, Moulinath; Woodroofe, Michael. Inconsistency of bootstrap: The Grenander estimator. Ann. Statist., Tome 38 (2010) no. 1, pp.  1953-1977. http://gdmltest.u-ga.fr/item/1278861239/