Concentration inequalities for order statistics

Type: Article

Publication Date: 2012-01-01

Citations: 46

DOI: https://doi.org/10.1214/ecp.v17-2210

Abstract

This note describes non-asymptotic variance and tail bounds for order statistics of samples of independent identically distributed random variables. When the sampling distribution belongs to a maximum domain of attraction, these bounds are checked to be asymptotically tight. When the sampling distribution has a non decreasing hazard rate, we derive an exponential Efron-Stein inequality for order statistics, that is an inequality connecting the logarithmic moment generating function of order statistics with exponential moments of Efron-Stein (jackknife) estimates of variance. This connection is used to derive variance and tail bounds for order statistics of Gaussian samples that are not within the scope of the Gaussian concentration inequality. Proofs are elementary and combine Rényi's representation of order statistics with the entropy approach to concentration of measure popularized by M. Ledoux.

Locations

  • arXiv (Cornell University) - View - PDF
  • HAL (Le Centre pour la Communication Scientifique Directe) - View
  • DataCite API - View
  • Electronic Communications in Probability - View - PDF

Similar Works

Action Title Year Authors
+ Inequalities for order statistics of samples from distributions with monotone hazard rate 2016 V. G. Ushakov
N. G. Ushakov
+ Concentration inequalities for order statistics Using the entropy method and Rényi's representation 2012 Stéphane Boucheron
Marlin U. Thomas
+ Moments of Order Statistics from Length-Biased Exponential Distribution and Associated Inference 2020 Zuber Akhter
Jagdish Saran
Kanika Verma
Narinder Pushkarna
+ Entropic Central Limit Theorem for Order Statistics 2022 Martina Cardone
Alex Dytso
Cynthia Rush
+ Order statistics of uniform, logistic and exponential distributions 2016 Collins O Okoyo
+ Exponential inequalities for tail probabilities of generalized order statistics 2005 Frank Marohn
+ PDF Chat On characterizations of continuous distributions in terms of moments of order statistics when the sample size is random 1998 Z. Grudzieú
Dominik Szynal
+ PDF Chat A Characterization of the Exponential Distribution by Order Statistics 1971 M. M. Desu
+ On the asymptotics of numbers of observations in random regions determined by order statistics 2011 Anna Dembińska
George Iliopoulos
+ The concentration inequalities of functions of independent random variables 2007 Xiaogang Zhang
+ Moment inequalities for order statistics with applications to characterizations of distributions 1991 Lesław Gajek
Ursula Gather
+ Characterization of the Exponential Distribution Using Lower Moments of Order Statistics 1975 Z. Govindarajulu
+ Limit theorems for order statistics from exponentials 2015 Yu Miao
Rujun Wang
André Adler
+ Order Statistics, Quantiles, and Coverages 2014 Jean Dickinson Gibbons
S. Chakraborti
+ Order Statistics, Quantiles, and Coverages 2010
+ Order Statistics, Quantiles, and Coverages 2020 Jean Dickinson Gibbons
S. Chakraborti
+ Variance estimation for order statistics and kernel-smoothed sample quantiles 2006 KY Cheung
Sms Lee
+ Improving the hartley-David-Gumbel bound for the mean of extreme order statistics 1990 N. Balakrishnan
+ On a Characterization of the Exponential Distribution by Order Statistics 1985 Maria Iwińska
+ A characterization of exponential distributions based on order statistics 1980 C. B. Bell
Y. Rama Krishna Sarma