Generalized confidence intervals for proportions of total variance in mixed linear models

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Exact confidence intervals for a proportion of total variance, based on pivotal quantities, only exist for mixed linear models having two variance components. Generalized confidence intervals (GCIs) introduced by Weerahandi [1993. Generalized confidence intervals (Corr: 94V89 p726). J. Am. Statist. Assoc. 88, 899-905] are based on generalized pivotal quantities (GPQs) and can be constructed for a much wider range of models. In this paper, the author investigates the coverage probabilities, as well as the utility of GCIs, for a proportion of total variance in mixed linear models having more than two variance components. Particular attention is given to the formation of GPQs and GCIs in mixed linear models having three variance components in situations where the data exhibit complete balance, partial balance, and partial imbalance. The GCI procedure is quite general and provides a useful method to construct confidence intervals in a variety of applications.

Original languageEnglish (US)
Pages (from-to)2394-2404
Number of pages11
JournalJournal of Statistical Planning and Inference
Volume137
Issue number7
DOIs
StatePublished - Jul 1 2007

Fingerprint

Generalized Confidence Interval
Mixed Linear Model
Pivotal Quantity
Proportion
Variance Components
Exact Confidence Interval
Partial
Coverage Probability
Confidence interval
Range of data

Keywords

  • Coverage probability
  • Crossed and nested designs
  • Variance components

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Applied Mathematics
  • Statistics and Probability

Cite this

Generalized confidence intervals for proportions of total variance in mixed linear models. / Burch, Brent D.

In: Journal of Statistical Planning and Inference, Vol. 137, No. 7, 01.07.2007, p. 2394-2404.

Research output: Contribution to journalArticle

@article{46937544c29b4c7cb721e0720aba95eb,
title = "Generalized confidence intervals for proportions of total variance in mixed linear models",
abstract = "Exact confidence intervals for a proportion of total variance, based on pivotal quantities, only exist for mixed linear models having two variance components. Generalized confidence intervals (GCIs) introduced by Weerahandi [1993. Generalized confidence intervals (Corr: 94V89 p726). J. Am. Statist. Assoc. 88, 899-905] are based on generalized pivotal quantities (GPQs) and can be constructed for a much wider range of models. In this paper, the author investigates the coverage probabilities, as well as the utility of GCIs, for a proportion of total variance in mixed linear models having more than two variance components. Particular attention is given to the formation of GPQs and GCIs in mixed linear models having three variance components in situations where the data exhibit complete balance, partial balance, and partial imbalance. The GCI procedure is quite general and provides a useful method to construct confidence intervals in a variety of applications.",
keywords = "Coverage probability, Crossed and nested designs, Variance components",
author = "Burch, {Brent D}",
year = "2007",
month = "7",
day = "1",
doi = "10.1016/j.jspi.2006.08.004",
language = "English (US)",
volume = "137",
pages = "2394--2404",
journal = "Journal of Statistical Planning and Inference",
issn = "0378-3758",
publisher = "Elsevier",
number = "7",

}

TY - JOUR

T1 - Generalized confidence intervals for proportions of total variance in mixed linear models

AU - Burch, Brent D

PY - 2007/7/1

Y1 - 2007/7/1

N2 - Exact confidence intervals for a proportion of total variance, based on pivotal quantities, only exist for mixed linear models having two variance components. Generalized confidence intervals (GCIs) introduced by Weerahandi [1993. Generalized confidence intervals (Corr: 94V89 p726). J. Am. Statist. Assoc. 88, 899-905] are based on generalized pivotal quantities (GPQs) and can be constructed for a much wider range of models. In this paper, the author investigates the coverage probabilities, as well as the utility of GCIs, for a proportion of total variance in mixed linear models having more than two variance components. Particular attention is given to the formation of GPQs and GCIs in mixed linear models having three variance components in situations where the data exhibit complete balance, partial balance, and partial imbalance. The GCI procedure is quite general and provides a useful method to construct confidence intervals in a variety of applications.

AB - Exact confidence intervals for a proportion of total variance, based on pivotal quantities, only exist for mixed linear models having two variance components. Generalized confidence intervals (GCIs) introduced by Weerahandi [1993. Generalized confidence intervals (Corr: 94V89 p726). J. Am. Statist. Assoc. 88, 899-905] are based on generalized pivotal quantities (GPQs) and can be constructed for a much wider range of models. In this paper, the author investigates the coverage probabilities, as well as the utility of GCIs, for a proportion of total variance in mixed linear models having more than two variance components. Particular attention is given to the formation of GPQs and GCIs in mixed linear models having three variance components in situations where the data exhibit complete balance, partial balance, and partial imbalance. The GCI procedure is quite general and provides a useful method to construct confidence intervals in a variety of applications.

KW - Coverage probability

KW - Crossed and nested designs

KW - Variance components

UR - http://www.scopus.com/inward/record.url?scp=33947283671&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947283671&partnerID=8YFLogxK

U2 - 10.1016/j.jspi.2006.08.004

DO - 10.1016/j.jspi.2006.08.004

M3 - Article

VL - 137

SP - 2394

EP - 2404

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

SN - 0378-3758

IS - 7

ER -