Graphical technique for comparing designs for random models

Juneyoung Lee, André I. Khuri

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Methods for comparing designs for a random (or mixed) linear model have focused primarily on criteria based on single-valued functions. In general, these functions are difficult to use, because of their complex forms, in addition to their dependence on the model's unknown variance components. In this paper, a graphical approach is presented for comparing designs for random models. The one-way model is used for illustration. The proposed approach is based on using quantiles of an estimator of a function of the variance components. The dependence of these quantiles on the true values of the variance components is depicted by plotting the so-called quantile dispersion graphs (QDGs), which provide a comprehensive picture of the quality of estimation obtained with a given design. The QDGs can therefore be used to compare several candidate designs. Two methods of estimation of variance components are considered, namely analysis of variance and maximum-likelihood estimation.

Original languageEnglish
Pages (from-to)933-947
Number of pages15
JournalJournal of Applied Statistics
Volume26
Issue number8
DOIs
Publication statusPublished - 1999 Jan 1
Externally publishedYes

Fingerprint

Quantile
Variance Components
Mixed Linear Model
Components of Variance
Single valued
Analysis of variance
Graph in graph theory
Maximum Likelihood Estimation
Model
Estimator
Unknown
Graphics
Design
Variance components
Graph

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Graphical technique for comparing designs for random models. / Lee, Juneyoung; Khuri, André I.

In: Journal of Applied Statistics, Vol. 26, No. 8, 01.01.1999, p. 933-947.

Research output: Contribution to journalArticle

@article{76a2803721f84b2bbb5cc3b9e961774f,
title = "Graphical technique for comparing designs for random models",
abstract = "Methods for comparing designs for a random (or mixed) linear model have focused primarily on criteria based on single-valued functions. In general, these functions are difficult to use, because of their complex forms, in addition to their dependence on the model's unknown variance components. In this paper, a graphical approach is presented for comparing designs for random models. The one-way model is used for illustration. The proposed approach is based on using quantiles of an estimator of a function of the variance components. The dependence of these quantiles on the true values of the variance components is depicted by plotting the so-called quantile dispersion graphs (QDGs), which provide a comprehensive picture of the quality of estimation obtained with a given design. The QDGs can therefore be used to compare several candidate designs. Two methods of estimation of variance components are considered, namely analysis of variance and maximum-likelihood estimation.",
author = "Juneyoung Lee and Khuri, {Andr{\'e} I.}",
year = "1999",
month = "1",
day = "1",
doi = "10.1080/02664769921945",
language = "English",
volume = "26",
pages = "933--947",
journal = "Journal of Applied Statistics",
issn = "0266-4763",
publisher = "Routledge",
number = "8",

}

TY - JOUR

T1 - Graphical technique for comparing designs for random models

AU - Lee, Juneyoung

AU - Khuri, André I.

PY - 1999/1/1

Y1 - 1999/1/1

N2 - Methods for comparing designs for a random (or mixed) linear model have focused primarily on criteria based on single-valued functions. In general, these functions are difficult to use, because of their complex forms, in addition to their dependence on the model's unknown variance components. In this paper, a graphical approach is presented for comparing designs for random models. The one-way model is used for illustration. The proposed approach is based on using quantiles of an estimator of a function of the variance components. The dependence of these quantiles on the true values of the variance components is depicted by plotting the so-called quantile dispersion graphs (QDGs), which provide a comprehensive picture of the quality of estimation obtained with a given design. The QDGs can therefore be used to compare several candidate designs. Two methods of estimation of variance components are considered, namely analysis of variance and maximum-likelihood estimation.

AB - Methods for comparing designs for a random (or mixed) linear model have focused primarily on criteria based on single-valued functions. In general, these functions are difficult to use, because of their complex forms, in addition to their dependence on the model's unknown variance components. In this paper, a graphical approach is presented for comparing designs for random models. The one-way model is used for illustration. The proposed approach is based on using quantiles of an estimator of a function of the variance components. The dependence of these quantiles on the true values of the variance components is depicted by plotting the so-called quantile dispersion graphs (QDGs), which provide a comprehensive picture of the quality of estimation obtained with a given design. The QDGs can therefore be used to compare several candidate designs. Two methods of estimation of variance components are considered, namely analysis of variance and maximum-likelihood estimation.

UR - http://www.scopus.com/inward/record.url?scp=0001789338&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0001789338&partnerID=8YFLogxK

U2 - 10.1080/02664769921945

DO - 10.1080/02664769921945

M3 - Article

VL - 26

SP - 933

EP - 947

JO - Journal of Applied Statistics

JF - Journal of Applied Statistics

SN - 0266-4763

IS - 8

ER -