Estimation of the precision matrix of multivariate Kotz type model

Amadou Sarr, Arjun K. Gupta

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

In this paper, the problem of estimating the precision matrix of a multivariate Kotz type model is considered. First, using the quadratic loss function, we prove that the unbiased estimator α0 A- 1, where A denotes the sample sum of product matrix, is dominated by a better constant multiple of A- 1, denoted by α0{star operator} A- 1. Secondly, a new class of shrinkage estimators of Σ- 1 is proposed. Moreover, the risk functions of α0 A- 1, α0{star operator} A- 1 and the proposed estimators are explicitly derived. It is shown that the proposed estimator dominates α0{star operator} A- 1, under the quadratic loss function. A simulation study is carried out which confirms these results. Improved estimator of tr (Σ- 1) is also obtained.

Original languageEnglish
Pages (from-to)742-752
Number of pages11
JournalJournal of Multivariate Analysis
Volume100
Issue number4
DOIs
Publication statusPublished - Apr 2009

Fingerprint

Quadratic Loss Function
Stars
Star
Estimator
Operator
Shrinkage Estimator
Risk Function
Matrix Product
Unbiased estimator
Mathematical operators
Simulation Study
Model
Denote
Loss function
Class

Keywords

  • 62C15
  • 62H12
  • Decision theoretic estimation
  • Estimation of the precision matrix
  • Multivariate Kotz type model
  • primary
  • Quadratic loss
  • secondary

ASJC Scopus subject areas

  • Statistics and Probability
  • Numerical Analysis
  • Statistics, Probability and Uncertainty

Cite this

Estimation of the precision matrix of multivariate Kotz type model. / Sarr, Amadou; Gupta, Arjun K.

In: Journal of Multivariate Analysis, Vol. 100, No. 4, 04.2009, p. 742-752.

Research output: Contribution to journalArticle

@article{66a5cc9f49834feca39701c896b4910c,
title = "Estimation of the precision matrix of multivariate Kotz type model",
abstract = "In this paper, the problem of estimating the precision matrix of a multivariate Kotz type model is considered. First, using the quadratic loss function, we prove that the unbiased estimator α0 A- 1, where A denotes the sample sum of product matrix, is dominated by a better constant multiple of A- 1, denoted by α0{star operator} A- 1. Secondly, a new class of shrinkage estimators of Σ- 1 is proposed. Moreover, the risk functions of α0 A- 1, α0{star operator} A- 1 and the proposed estimators are explicitly derived. It is shown that the proposed estimator dominates α0{star operator} A- 1, under the quadratic loss function. A simulation study is carried out which confirms these results. Improved estimator of tr (Σ- 1) is also obtained.",
keywords = "62C15, 62H12, Decision theoretic estimation, Estimation of the precision matrix, Multivariate Kotz type model, primary, Quadratic loss, secondary",
author = "Amadou Sarr and Gupta, {Arjun K.}",
year = "2009",
month = "4",
doi = "10.1016/j.jmva.2008.08.001",
language = "English",
volume = "100",
pages = "742--752",
journal = "Journal of Multivariate Analysis",
issn = "0047-259X",
publisher = "Academic Press Inc.",
number = "4",

}

TY - JOUR

T1 - Estimation of the precision matrix of multivariate Kotz type model

AU - Sarr, Amadou

AU - Gupta, Arjun K.

PY - 2009/4

Y1 - 2009/4

N2 - In this paper, the problem of estimating the precision matrix of a multivariate Kotz type model is considered. First, using the quadratic loss function, we prove that the unbiased estimator α0 A- 1, where A denotes the sample sum of product matrix, is dominated by a better constant multiple of A- 1, denoted by α0{star operator} A- 1. Secondly, a new class of shrinkage estimators of Σ- 1 is proposed. Moreover, the risk functions of α0 A- 1, α0{star operator} A- 1 and the proposed estimators are explicitly derived. It is shown that the proposed estimator dominates α0{star operator} A- 1, under the quadratic loss function. A simulation study is carried out which confirms these results. Improved estimator of tr (Σ- 1) is also obtained.

AB - In this paper, the problem of estimating the precision matrix of a multivariate Kotz type model is considered. First, using the quadratic loss function, we prove that the unbiased estimator α0 A- 1, where A denotes the sample sum of product matrix, is dominated by a better constant multiple of A- 1, denoted by α0{star operator} A- 1. Secondly, a new class of shrinkage estimators of Σ- 1 is proposed. Moreover, the risk functions of α0 A- 1, α0{star operator} A- 1 and the proposed estimators are explicitly derived. It is shown that the proposed estimator dominates α0{star operator} A- 1, under the quadratic loss function. A simulation study is carried out which confirms these results. Improved estimator of tr (Σ- 1) is also obtained.

KW - 62C15

KW - 62H12

KW - Decision theoretic estimation

KW - Estimation of the precision matrix

KW - Multivariate Kotz type model

KW - primary

KW - Quadratic loss

KW - secondary

UR - http://www.scopus.com/inward/record.url?scp=58349100663&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58349100663&partnerID=8YFLogxK

U2 - 10.1016/j.jmva.2008.08.001

DO - 10.1016/j.jmva.2008.08.001

M3 - Article

VL - 100

SP - 742

EP - 752

JO - Journal of Multivariate Analysis

JF - Journal of Multivariate Analysis

SN - 0047-259X

IS - 4

ER -