Robust and efficient mean estimation: approach based on the properties of self-normalized sums

06/02/2020
by   Stanislav Minsker, et al.
0

Let X be a random variable with unknown mean and finite variance. We present a new estimator of the mean of X that is robust with respect to the possible presence of outliers in the sample, provides tight sub-Gaussian deviation guarantees without any additional assumptions on the shape or tails of the distribution, and moreover is asymptotically efficient. This is the first estimator that provably combines all these qualities in one package. Our construction is inspired by robustness properties possessed by the self-normalized sums. Finally, theoretical findings are supplemented by numerical simulations highlighting the strong performance of the proposed estimator in comparison with previously known techniques.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/16/2021

Self-normalized Cramer moderate deviations for a supercritical Galton-Watson process

Let (Z_n)_n≥0 be a supercritical Galton-Watson process. Consider the Lot...
research
11/17/2020

Optimal Sub-Gaussian Mean Estimation in ℝ

We revisit the problem of estimating the mean of a real-valued distribut...
research
12/12/2019

Finite sample properties of parametric MMD estimation: robustness to misspecification and dependence

Many works in statistics aim at designing a universal estimation procedu...
research
02/24/2022

U-statistics of growing order and sub-Gaussian mean estimators with sharp constants

This paper addresses the following question: given a sample of i.i.d. ra...
research
06/30/2021

Do we need to estimate the variance in robust mean estimation?

This paper studies robust mean estimators for distributions with only fi...
research
11/09/2019

Estimation in Poisson Noise: Properties of the Conditional Mean Estimator

This paper considers estimation of a random variable in Poisson noise wi...

Please sign up or login with your details

Forgot password? Click here to reset