Mean driven balance and uniformly best linear unbiased estimators

Roman Zmyślony, João T. Mexia, Francisco Carvalho, Inês J. Sequeira

Research output: Contribution to journalArticle

Abstract

The equivalence of ordinary least squares estimators (OLSE) and Gauss–Markov estimators for models with variance–covariance matrix (Formula presented.) is extended to derive a necessary and sufficient balance condition for mixed models with mean vector (Formula presented.) , with (Formula presented.) an incidence matrix, having OLSE for (Formula presented.) that are best linear unbiased estimator whatever the variance components. This approach leads to least squares like estimators for variance components. To illustrate the range of applications for the balance condition, interesting special models are considered.

Original languageEnglish
Pages (from-to)43-53
Number of pages11
JournalStatistical Papers
Volume57
Issue number1
DOIs
Publication statusPublished - 1 Mar 2016

Fingerprint

Best Linear Unbiased Estimator
Ordinary Least Squares Estimator
Variance Components
Estimator
Variance-covariance Matrix
Incidence Matrix
Mixed Model
Least Squares
Equivalence
Sufficient
Necessary
Model
Range of data
Ordinary least squares
Variance components
Least squares estimator

Keywords

  • Kruskal condition
  • OLSE
  • Orthogonal block structure models
  • UBLUE

Cite this

Zmyślony, Roman ; Mexia, João T. ; Carvalho, Francisco ; Sequeira, Inês J. / Mean driven balance and uniformly best linear unbiased estimators. In: Statistical Papers. 2016 ; Vol. 57, No. 1. pp. 43-53.
@article{14c182865c2544959941070f3ecf2614,
title = "Mean driven balance and uniformly best linear unbiased estimators",
abstract = "The equivalence of ordinary least squares estimators (OLSE) and Gauss–Markov estimators for models with variance–covariance matrix (Formula presented.) is extended to derive a necessary and sufficient balance condition for mixed models with mean vector (Formula presented.) , with (Formula presented.) an incidence matrix, having OLSE for (Formula presented.) that are best linear unbiased estimator whatever the variance components. This approach leads to least squares like estimators for variance components. To illustrate the range of applications for the balance condition, interesting special models are considered.",
keywords = "Kruskal condition, OLSE, Orthogonal block structure models, UBLUE",
author = "Roman Zmyślony and Mexia, {Jo{\~a}o T.} and Francisco Carvalho and Sequeira, {In{\^e}s J.}",
note = "sem pdf conforme despacho. CMA/FCT/UNL (PEst-OE/MAT/UI0297/2011)",
year = "2016",
month = "3",
day = "1",
doi = "10.1007/s00362-014-0638-y",
language = "English",
volume = "57",
pages = "43--53",
journal = "Statistical Papers",
issn = "0932-5026",
publisher = "Springer",
number = "1",

}

Mean driven balance and uniformly best linear unbiased estimators. / Zmyślony, Roman; Mexia, João T.; Carvalho, Francisco; Sequeira, Inês J.

In: Statistical Papers, Vol. 57, No. 1, 01.03.2016, p. 43-53.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Mean driven balance and uniformly best linear unbiased estimators

AU - Zmyślony, Roman

AU - Mexia, João T.

AU - Carvalho, Francisco

AU - Sequeira, Inês J.

N1 - sem pdf conforme despacho. CMA/FCT/UNL (PEst-OE/MAT/UI0297/2011)

PY - 2016/3/1

Y1 - 2016/3/1

N2 - The equivalence of ordinary least squares estimators (OLSE) and Gauss–Markov estimators for models with variance–covariance matrix (Formula presented.) is extended to derive a necessary and sufficient balance condition for mixed models with mean vector (Formula presented.) , with (Formula presented.) an incidence matrix, having OLSE for (Formula presented.) that are best linear unbiased estimator whatever the variance components. This approach leads to least squares like estimators for variance components. To illustrate the range of applications for the balance condition, interesting special models are considered.

AB - The equivalence of ordinary least squares estimators (OLSE) and Gauss–Markov estimators for models with variance–covariance matrix (Formula presented.) is extended to derive a necessary and sufficient balance condition for mixed models with mean vector (Formula presented.) , with (Formula presented.) an incidence matrix, having OLSE for (Formula presented.) that are best linear unbiased estimator whatever the variance components. This approach leads to least squares like estimators for variance components. To illustrate the range of applications for the balance condition, interesting special models are considered.

KW - Kruskal condition

KW - OLSE

KW - Orthogonal block structure models

KW - UBLUE

UR - http://www.scopus.com/inward/record.url?scp=84964446956&partnerID=8YFLogxK

U2 - 10.1007/s00362-014-0638-y

DO - 10.1007/s00362-014-0638-y

M3 - Article

VL - 57

SP - 43

EP - 53

JO - Statistical Papers

JF - Statistical Papers

SN - 0932-5026

IS - 1

ER -