Applying Skovgaard's modified directed likelihood statistic to mixed linear models

Ben Lyons, Dawn Peters

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

The introduction of software to calculate maximum likelihood estimates for mixed linear models has made likelihood estimation a practical alternative to methods based on sums of squares. Likelihood based tests and confidence intervals, however, may be misleading in problems with small sample sizes. This paper discusses an adjusted version of the directed log-likelihood statistic for mixed models that is highly accurate for testing one parameter hypotheses. Introduced by Skovgaard (1996, Journal of the Bernoulli Society, 2, 145-165), we show in mixed models that the statistic has a simple compact form that may be obtained from standard software. Simulation studies indicate that this statistic is more accurate than many of the specialized procedures that have been advocated.

Original languageEnglish (US)
Pages (from-to)225-242
Number of pages18
JournalJournal of Statistical Computation and Simulation
Volume65
Issue number3
StatePublished - 2000
Externally publishedYes

Fingerprint

Mixed Linear Model
Statistic
Likelihood
Mixed Model
Statistics
Software
Small Sample Size
Sum of squares
Maximum Likelihood Estimate
Bernoulli
Maximum likelihood
Confidence interval
Simulation Study
Calculate
Testing
Alternatives
Mixed model

Keywords

  • Asymptotics
  • Likelihood
  • Mixed models
  • Repeated measures
  • Small sample inference
  • Variance components

ASJC Scopus subject areas

  • Applied Mathematics
  • Modeling and Simulation
  • Statistics and Probability

Cite this

Applying Skovgaard's modified directed likelihood statistic to mixed linear models. / Lyons, Ben; Peters, Dawn.

In: Journal of Statistical Computation and Simulation, Vol. 65, No. 3, 2000, p. 225-242.

Research output: Contribution to journalArticle

@article{ac1d5dffa7a04fb2a71cad1170b72a11,
title = "Applying Skovgaard's modified directed likelihood statistic to mixed linear models",
abstract = "The introduction of software to calculate maximum likelihood estimates for mixed linear models has made likelihood estimation a practical alternative to methods based on sums of squares. Likelihood based tests and confidence intervals, however, may be misleading in problems with small sample sizes. This paper discusses an adjusted version of the directed log-likelihood statistic for mixed models that is highly accurate for testing one parameter hypotheses. Introduced by Skovgaard (1996, Journal of the Bernoulli Society, 2, 145-165), we show in mixed models that the statistic has a simple compact form that may be obtained from standard software. Simulation studies indicate that this statistic is more accurate than many of the specialized procedures that have been advocated.",
keywords = "Asymptotics, Likelihood, Mixed models, Repeated measures, Small sample inference, Variance components",
author = "Ben Lyons and Dawn Peters",
year = "2000",
language = "English (US)",
volume = "65",
pages = "225--242",
journal = "Journal of Statistical Computation and Simulation",
issn = "0094-9655",
publisher = "Taylor and Francis Ltd.",
number = "3",

}

TY - JOUR

T1 - Applying Skovgaard's modified directed likelihood statistic to mixed linear models

AU - Lyons, Ben

AU - Peters, Dawn

PY - 2000

Y1 - 2000

N2 - The introduction of software to calculate maximum likelihood estimates for mixed linear models has made likelihood estimation a practical alternative to methods based on sums of squares. Likelihood based tests and confidence intervals, however, may be misleading in problems with small sample sizes. This paper discusses an adjusted version of the directed log-likelihood statistic for mixed models that is highly accurate for testing one parameter hypotheses. Introduced by Skovgaard (1996, Journal of the Bernoulli Society, 2, 145-165), we show in mixed models that the statistic has a simple compact form that may be obtained from standard software. Simulation studies indicate that this statistic is more accurate than many of the specialized procedures that have been advocated.

AB - The introduction of software to calculate maximum likelihood estimates for mixed linear models has made likelihood estimation a practical alternative to methods based on sums of squares. Likelihood based tests and confidence intervals, however, may be misleading in problems with small sample sizes. This paper discusses an adjusted version of the directed log-likelihood statistic for mixed models that is highly accurate for testing one parameter hypotheses. Introduced by Skovgaard (1996, Journal of the Bernoulli Society, 2, 145-165), we show in mixed models that the statistic has a simple compact form that may be obtained from standard software. Simulation studies indicate that this statistic is more accurate than many of the specialized procedures that have been advocated.

KW - Asymptotics

KW - Likelihood

KW - Mixed models

KW - Repeated measures

KW - Small sample inference

KW - Variance components

UR - http://www.scopus.com/inward/record.url?scp=0034349016&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034349016&partnerID=8YFLogxK

M3 - Article

VL - 65

SP - 225

EP - 242

JO - Journal of Statistical Computation and Simulation

JF - Journal of Statistical Computation and Simulation

SN - 0094-9655

IS - 3

ER -