Inference of nested variance components in a longitudinal myopia intervention trial

Chuhsing Kate Hsiao, Miao-Yu Tsai, Ho Min Chen

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This paper was motivated by a double-blind randomized clinical trial of myopia intervention. In addition to the primary goal of comparing treatment effects, we are concerned with the modelling of correlation that may come from two possible sources, one among the longitudinal observations and the other between measurements taken from both eyes per subject. The data are nested repeated measurements. We suggest three models for analysis. Each one expresses the correlation differently in various covariance structures. We articulate their differences and describe the implementations in estimation using commercial statistical software. The computer output can be further utilized to perform model selection with Schwarz criterion. Simulation studies are conducted to evaluate the performance under each model. Data of the myopia intervention trial are reanalysed with these models for illustration. The results indicate that atropine is more effective in reducing the progression rate, the rates are homogeneous across subjects, and, among the suggested models, the one with independent random effects of two eyes fits best. We conclude that model selection is a crucial step before making inference with estimates; otherwise the correlation may be attributed incorrectly to a different mechanism. The same conclusion applies to other variance components as well.

Original languageEnglish
Pages (from-to)3251-3267
Number of pages17
JournalStatistics in Medicine
Volume24
Issue number21
DOIs
Publication statusPublished - 2005 Nov 15

Fingerprint

Variance Components
Myopia
Atropine
Model Selection
Software
Randomized Controlled Trials
Randomized Clinical Trial
Statistical Software
Repeated Measurements
Covariance Structure
Treatment Effects
Random Effects
Progression
Model
Express
Simulation Study
Evaluate
Output
Modeling
Estimate

All Science Journal Classification (ASJC) codes

  • Epidemiology
  • Statistics and Probability

Cite this

Hsiao, Chuhsing Kate ; Tsai, Miao-Yu ; Chen, Ho Min. / Inference of nested variance components in a longitudinal myopia intervention trial. In: Statistics in Medicine. 2005 ; Vol. 24, No. 21. pp. 3251-3267.
@article{93efb22ecc4e4bf1b00736f28a4848e0,
title = "Inference of nested variance components in a longitudinal myopia intervention trial",
abstract = "This paper was motivated by a double-blind randomized clinical trial of myopia intervention. In addition to the primary goal of comparing treatment effects, we are concerned with the modelling of correlation that may come from two possible sources, one among the longitudinal observations and the other between measurements taken from both eyes per subject. The data are nested repeated measurements. We suggest three models for analysis. Each one expresses the correlation differently in various covariance structures. We articulate their differences and describe the implementations in estimation using commercial statistical software. The computer output can be further utilized to perform model selection with Schwarz criterion. Simulation studies are conducted to evaluate the performance under each model. Data of the myopia intervention trial are reanalysed with these models for illustration. The results indicate that atropine is more effective in reducing the progression rate, the rates are homogeneous across subjects, and, among the suggested models, the one with independent random effects of two eyes fits best. We conclude that model selection is a crucial step before making inference with estimates; otherwise the correlation may be attributed incorrectly to a different mechanism. The same conclusion applies to other variance components as well.",
author = "Hsiao, {Chuhsing Kate} and Miao-Yu Tsai and Chen, {Ho Min}",
year = "2005",
month = "11",
day = "15",
doi = "10.1002/sim.2211",
language = "English",
volume = "24",
pages = "3251--3267",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "21",

}

Inference of nested variance components in a longitudinal myopia intervention trial. / Hsiao, Chuhsing Kate; Tsai, Miao-Yu; Chen, Ho Min.

In: Statistics in Medicine, Vol. 24, No. 21, 15.11.2005, p. 3251-3267.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Inference of nested variance components in a longitudinal myopia intervention trial

AU - Hsiao, Chuhsing Kate

AU - Tsai, Miao-Yu

AU - Chen, Ho Min

PY - 2005/11/15

Y1 - 2005/11/15

N2 - This paper was motivated by a double-blind randomized clinical trial of myopia intervention. In addition to the primary goal of comparing treatment effects, we are concerned with the modelling of correlation that may come from two possible sources, one among the longitudinal observations and the other between measurements taken from both eyes per subject. The data are nested repeated measurements. We suggest three models for analysis. Each one expresses the correlation differently in various covariance structures. We articulate their differences and describe the implementations in estimation using commercial statistical software. The computer output can be further utilized to perform model selection with Schwarz criterion. Simulation studies are conducted to evaluate the performance under each model. Data of the myopia intervention trial are reanalysed with these models for illustration. The results indicate that atropine is more effective in reducing the progression rate, the rates are homogeneous across subjects, and, among the suggested models, the one with independent random effects of two eyes fits best. We conclude that model selection is a crucial step before making inference with estimates; otherwise the correlation may be attributed incorrectly to a different mechanism. The same conclusion applies to other variance components as well.

AB - This paper was motivated by a double-blind randomized clinical trial of myopia intervention. In addition to the primary goal of comparing treatment effects, we are concerned with the modelling of correlation that may come from two possible sources, one among the longitudinal observations and the other between measurements taken from both eyes per subject. The data are nested repeated measurements. We suggest three models for analysis. Each one expresses the correlation differently in various covariance structures. We articulate their differences and describe the implementations in estimation using commercial statistical software. The computer output can be further utilized to perform model selection with Schwarz criterion. Simulation studies are conducted to evaluate the performance under each model. Data of the myopia intervention trial are reanalysed with these models for illustration. The results indicate that atropine is more effective in reducing the progression rate, the rates are homogeneous across subjects, and, among the suggested models, the one with independent random effects of two eyes fits best. We conclude that model selection is a crucial step before making inference with estimates; otherwise the correlation may be attributed incorrectly to a different mechanism. The same conclusion applies to other variance components as well.

UR - http://www.scopus.com/inward/record.url?scp=27644473696&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27644473696&partnerID=8YFLogxK

U2 - 10.1002/sim.2211

DO - 10.1002/sim.2211

M3 - Article

C2 - 16206249

AN - SCOPUS:27644473696

VL - 24

SP - 3251

EP - 3267

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 21

ER -