Universal domination and stochastic domination: U-admissibility and U- inadmissibility of the least squares estimator

DOI10.1214/aos/1176347014zbMath0674.62007OpenAlexW1999971690MaRDI QIDQ1121606

Publication date: 1989

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aos/1176347014

zbMATH Keywords

normal distribution squared error loss least squares estimator stochastic domination identity covariance matrix standard linear model universal domination James-Stein positive part estimator James-Stein type estimators U-admissible U-inadmissible universal class of losses universally inadmissible zero mean vector

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07) Point estimation (62F10) Admissibility in statistical decision theory (62C15) General considerations in statistical decision theory (62C05)

Related Items (9)

Universal admissibility in second order asymptotics ⋮ A note on universal admissibility of scale parameter estimators ⋮ Larry Brown's work on admissibility ⋮ Universal inadmissibility of least squares estimator ⋮ Improved confidence sets of spherically symmetric distributions ⋮ Stein estimation -- a review ⋮ Applied regression analysis bibliography update 1988-89 ⋮ Comparison of estimators of the location parameter using pitman's closeness criterion ⋮ Universal Domination and Stochastic Domination—an Improved lower Bound for the Dimensionality

This page was built for publication: Universal domination and stochastic domination: U-admissibility and U- inadmissibility of the least squares estimator