Aarhus University Seal / Aarhus Universitets segl

Tests and Confidence Intervals for an Extended Variance Component Using the Modified Likelihood Ratio Statistic

Publikation: Working paper/Preprint Working paperForskning

Standard

Tests and Confidence Intervals for an Extended Variance Component Using the Modified Likelihood Ratio Statistic. / Christensen, Ole Fredslund; Frydenberg, Morten; Jensen, Jens Ledet; Pedersen, Jørgen Granfeldt.

2005.

Publikation: Working paper/Preprint Working paperForskning

Harvard

APA

CBE

MLA

Vancouver

Author

Bibtex

@techreport{0c2a1930b8c311dabee902004c4f4f50,
title = "Tests and Confidence Intervals for an Extended Variance Component Using the Modified Likelihood Ratio Statistic",
abstract = "The large deviation modified likelihood ratio statistic is studied for testing a variance component equal to a specified value. Formulas are presented in the general balanced case, whereas in the unbalanced case only the one-way random effects model is studied. Simulation studies are presented, showing that the normal approximation to the large deviation modified likelihood ratio statistic gives confidence intervals for variance components with coverage probabilities very close to the nominal confidence coefficient.",
author = "Christensen, {Ole Fredslund} and Morten Frydenberg and Jensen, {Jens Ledet} and Pedersen, {J{\o}rgen Granfeldt}",
year = "2005",
language = "English",
type = "WorkingPaper",

}

RIS

TY - UNPB

T1 - Tests and Confidence Intervals for an Extended Variance Component Using the Modified Likelihood Ratio Statistic

AU - Christensen, Ole Fredslund

AU - Frydenberg, Morten

AU - Jensen, Jens Ledet

AU - Pedersen, Jørgen Granfeldt

PY - 2005

Y1 - 2005

N2 - The large deviation modified likelihood ratio statistic is studied for testing a variance component equal to a specified value. Formulas are presented in the general balanced case, whereas in the unbalanced case only the one-way random effects model is studied. Simulation studies are presented, showing that the normal approximation to the large deviation modified likelihood ratio statistic gives confidence intervals for variance components with coverage probabilities very close to the nominal confidence coefficient.

AB - The large deviation modified likelihood ratio statistic is studied for testing a variance component equal to a specified value. Formulas are presented in the general balanced case, whereas in the unbalanced case only the one-way random effects model is studied. Simulation studies are presented, showing that the normal approximation to the large deviation modified likelihood ratio statistic gives confidence intervals for variance components with coverage probabilities very close to the nominal confidence coefficient.

M3 - Working paper

BT - Tests and Confidence Intervals for an Extended Variance Component Using the Modified Likelihood Ratio Statistic

ER -