Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Optimal shrinkage estimator for high-dimensional mean vector
Stockholms universitet, Naturvetenskapliga fakulteten, Matematiska institutionen.ORCID-id: 0000-0001-7855-8221
2019 (Engelska)Ingår i: Journal of Multivariate Analysis, ISSN 0047-259X, E-ISSN 1095-7243, Vol. 170, s. 63-79Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

In this paper we derive the optimal linear shrinkage estimator for the high-dimensional mean vector using random matrix theory. The results are obtained under the assumption that both the dimension $p$ and the sample size $n$ tend to infinity in such a way that $p∕n\to c\in(0,\infty)$. Under weak conditions imposed on the underlying data generating mechanism, we find the asymptotic equivalents to the optimal shrinkage intensities and estimate them consistently. The proposed nonparametric estimator for the high-dimensional mean vector has a simple structure and is proven to minimize asymptotically, with probability 1, the quadratic loss when $c\in(0,1)$. When $c\in(1,\infty)$ we modify the estimator by using a feasible estimator for the precision covariance matrix. To this end, an exhaustive simulation study and an application to real data are provided where the proposed estimator is compared with known benchmarks from the literature. It turns out that the existing estimators of the mean vector, including the new proposal, converge to the sample mean vector when the true mean vector has an unbounded Euclidean norm.

Ort, förlag, år, upplaga, sidor
2019. Vol. 170, s. 63-79
Nyckelord [en]
Large-dimensional asymptotics, Mean vector estimation, Random matrix theory, Shrinkage estimator
Nationell ämneskategori
Sannolikhetsteori och statistik
Identifikatorer
URN: urn:nbn:se:su:diva-164879DOI: 10.1016/j.jmva.2018.07.004ISI: 000457205300006OAI: oai:DiVA.org:su-164879DiVA, id: diva2:1280599
Tillgänglig från: 2019-01-20 Skapad: 2019-01-20 Senast uppdaterad: 2019-03-04Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextarXiv:1610.09292

Sök vidare i DiVA

Av författaren/redaktören
Bodnar, Taras
Av organisationen
Matematiska institutionen
I samma tidskrift
Journal of Multivariate Analysis
Sannolikhetsteori och statistik

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 48 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf