A note on improving on a vector of coordinate-wise estimators of non-negative means via shrinkage

Yuan Tsung Chang; Takeru Matsuda; William E. Strawderman

doi:10.1016/j.spl.2019.06.005

A note on improving on a vector of coordinate-wise estimators of non-negative means via shrinkage

Yuan Tsung Chang
, Takeru Matsuda
, William E. Strawderman

School of Arts and Sciences, Statistics

Research output: Contribution to journal › Article › peer-review

Abstract

We study improved shrinkage estimation of a vector of non-negative means. We concentrate on the Gaussian case with known scale, but do not necessarily assume the initial estimator is minimax. As a result, we find improved shrinkage estimators in fewer than 3 dimension in certain cases. Generalized Bayes estimators which may be improved via shrinkage in 1 and 2 dimensions illustrate the result. We also consider improved positive part estimators.

Original language	English (US)
Pages (from-to)	143-150
Number of pages	8
Journal	Statistics and Probability Letters
Volume	153
DOIs	https://doi.org/10.1016/j.spl.2019.06.005
State	Published - Oct 2019

All Science Journal Classification (ASJC) codes

Statistics and Probability
Statistics, Probability and Uncertainty

Keywords

Generalized Bayes estimator
Katz estimator
Pseudo-Bayes estimator
Stein estimator

Access to Document

10.1016/j.spl.2019.06.005

Cite this

@article{8dcb93da1ef749ee822136f105ba51ab,

title = "A note on improving on a vector of coordinate-wise estimators of non-negative means via shrinkage",

abstract = "We study improved shrinkage estimation of a vector of non-negative means. We concentrate on the Gaussian case with known scale, but do not necessarily assume the initial estimator is minimax. As a result, we find improved shrinkage estimators in fewer than 3 dimension in certain cases. Generalized Bayes estimators which may be improved via shrinkage in 1 and 2 dimensions illustrate the result. We also consider improved positive part estimators.",

keywords = "Generalized Bayes estimator, Katz estimator, Pseudo-Bayes estimator, Stein estimator",

author = "Chang, \{Yuan Tsung\} and Takeru Matsuda and Strawderman, \{William E.\}",

note = "Publisher Copyright: {\textcopyright} 2019 Elsevier B.V.",

year = "2019",

month = oct,

doi = "10.1016/j.spl.2019.06.005",

language = "English (US)",

volume = "153",

pages = "143--150",

journal = "Statistics and Probability Letters",

issn = "0167-7152",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - A note on improving on a vector of coordinate-wise estimators of non-negative means via shrinkage

AU - Chang, Yuan Tsung

AU - Matsuda, Takeru

AU - Strawderman, William E.

PY - 2019/10

Y1 - 2019/10

N2 - We study improved shrinkage estimation of a vector of non-negative means. We concentrate on the Gaussian case with known scale, but do not necessarily assume the initial estimator is minimax. As a result, we find improved shrinkage estimators in fewer than 3 dimension in certain cases. Generalized Bayes estimators which may be improved via shrinkage in 1 and 2 dimensions illustrate the result. We also consider improved positive part estimators.

AB - We study improved shrinkage estimation of a vector of non-negative means. We concentrate on the Gaussian case with known scale, but do not necessarily assume the initial estimator is minimax. As a result, we find improved shrinkage estimators in fewer than 3 dimension in certain cases. Generalized Bayes estimators which may be improved via shrinkage in 1 and 2 dimensions illustrate the result. We also consider improved positive part estimators.

KW - Generalized Bayes estimator

KW - Katz estimator

KW - Pseudo-Bayes estimator

KW - Stein estimator

UR - https://www.scopus.com/pages/publications/85067652351

UR - https://www.scopus.com/pages/publications/85067652351#tab=citedBy

U2 - 10.1016/j.spl.2019.06.005

DO - 10.1016/j.spl.2019.06.005

M3 - Article

AN - SCOPUS:85067652351

SN - 0167-7152

VL - 153

SP - 143

EP - 150

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

ER -

A note on improving on a vector of coordinate-wise estimators of non-negative means via shrinkage

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this