scispace - formally typeset
Open AccessJournal ArticleDOI

Functional jackknifing: Rationality and general asymptotics

Pranab Kumar Sen
- 01 Mar 1988 - 
- Vol. 16, Iss: 1, pp 450-469
TLDR
In this paper, a technique de jackknife is proposed for estimating the variance and representations of distributions asymptotiques du second-ordre for les estimateurs du jackknife classiques.
Abstract
On considere une technique de jackknife a deux niveaux pour l'estimation de la variance et des representations de distributions asymptotiques du second-ordre pour les estimateurs du jackknife classiques

read more

Content maybe subject to copyright    Report

Citations
More filters
Journal ArticleDOI

Differentiability of Statistical Functionals and Consistency of the Jackknife

Jun Shao
- 01 Mar 1993 - 
TL;DR: In this article, the smoothness of T through the differentiability of T and establishes some general results for the consistency of the jackknife variance estimators of the functional T. The results are applied to some examples in which the statistics $T(F_n)$ are L-, M-and some test statistics.
Journal ArticleDOI

Effect of the initial estimator on the asymptotic behavior of one-step M-estimator

TL;DR: In this paper, the asymptotic distribution of n(Mn(1)-Mn) is studied; it is typically non-normal and reveals the role of the initial estimator Mn(0).
Book ChapterDOI

Introduction to Hoeffding (1948) A Class of Statistics with Asymptotically Normal Distribution

TL;DR: Wassily Hoeffding was born on June 12, 1914 in Mustamaki, Finland, near St Petersburg (now Leningrad), USSR as mentioned in this paper, where the Bolshevik movement was quite intense and consolidated under the Lenin dictatorship in the Civil War of 1918-20.
Journal ArticleDOI

Von Mises Approximation of the Critical Value of a Test

TL;DR: In this paper, a von Mises approximation of the critical value of a test and a saddlepoint approximation of it are proposed to compute quantiles of complicated test statistics with a complicated distribution function, which is a very common situation in robustness studies.