Home > Research > Publications & Outputs > Meta-analysis of ordinal outcomes using individ...
View graph of relations

Meta-analysis of ordinal outcomes using individual patient data.

Research output: Contribution to journalJournal articlepeer-review

Published

Standard

Meta-analysis of ordinal outcomes using individual patient data. / Whitehead, Anne; Higgins, Julian P. T.; Omar, Rumana Z.; Savaluny, Elly.

In: Statistics in Medicine, Vol. 20, No. 15, 15.08.2001, p. 2243-2260.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Whitehead, A, Higgins, JPT, Omar, RZ & Savaluny, E 2001, 'Meta-analysis of ordinal outcomes using individual patient data.', Statistics in Medicine, vol. 20, no. 15, pp. 2243-2260. https://doi.org/10.1002/sim.919

APA

Whitehead, A., Higgins, J. P. T., Omar, R. Z., & Savaluny, E. (2001). Meta-analysis of ordinal outcomes using individual patient data. Statistics in Medicine, 20(15), 2243-2260. https://doi.org/10.1002/sim.919

Vancouver

Whitehead A, Higgins JPT, Omar RZ, Savaluny E. Meta-analysis of ordinal outcomes using individual patient data. Statistics in Medicine. 2001 Aug 15;20(15):2243-2260. https://doi.org/10.1002/sim.919

Author

Whitehead, Anne ; Higgins, Julian P. T. ; Omar, Rumana Z. ; Savaluny, Elly. / Meta-analysis of ordinal outcomes using individual patient data. In: Statistics in Medicine. 2001 ; Vol. 20, No. 15. pp. 2243-2260.

Bibtex

@article{bbca604191fb418e84d7dd63ab511b44,
title = "Meta-analysis of ordinal outcomes using individual patient data.",
abstract = "Meta-analyses are being undertaken in an increasing diversity of diseases and conditions, some of which involve outcomes measured on an ordered categorical scale. We consider methodology for undertaking a meta-analysis on individual patient data for an ordinal response. The approach is based on the proportional odds model, in which the treatment effect is represented by the log-odds ratio. A general framework is proposed for fixed and random effect models. Tests of the validity of the various assumptions made in the meta-analysis models, such as a global test of the assumption of proportional odds between treatments, are presented. The combination of studies with different definitions or numbers of response categories is discussed. The methods are illustrated on two data sets, in a classical framework using SAS and MLn and in a Bayesian framework using BUGS. The relative merits of the three software packages for such meta-analyses are discussed. Copyright {\textcopyright} 2001 John Wiley & Sons, Ltd.",
author = "Anne Whitehead and Higgins, {Julian P. T.} and Omar, {Rumana Z.} and Elly Savaluny",
note = "This book consists of twelve chapters covering 305 pages. Chapters 1 and 2 are introductory; providing a rationale for meta-analysis and the key concepts and terminology. Chapters 3 and 4 provide a general framework for meta-analysis based on study estimates of treatment difference and their variances, extending the approach previously published by the author in Statistics in Medicine. Chapters 5 and 9-12 contain mainly original research by the author covering the topics of meta-analysis using individual patient data, dealing with non-standard sets of data, inclusion of trials with different designs, a Bayesian approach to meta-analysis and sequential methods for meta-analysis. The author has published 5 papers based on the work described in these chapters in journals such as Statistics in Medicine. There is ongoing research based on the contents of Chapter 12. Chapters 6-8 on dealing with heterogeneity, presentation and interpretation of results and selection bias mainly present methods which have appeared in the literature by other authors. RAE_import_type : Journal article RAE_uoa_type : Statistics and Operational Research",
year = "2001",
month = aug,
day = "15",
doi = "10.1002/sim.919",
language = "English",
volume = "20",
pages = "2243--2260",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "15",

}

RIS

TY - JOUR

T1 - Meta-analysis of ordinal outcomes using individual patient data.

AU - Whitehead, Anne

AU - Higgins, Julian P. T.

AU - Omar, Rumana Z.

AU - Savaluny, Elly

N1 - This book consists of twelve chapters covering 305 pages. Chapters 1 and 2 are introductory; providing a rationale for meta-analysis and the key concepts and terminology. Chapters 3 and 4 provide a general framework for meta-analysis based on study estimates of treatment difference and their variances, extending the approach previously published by the author in Statistics in Medicine. Chapters 5 and 9-12 contain mainly original research by the author covering the topics of meta-analysis using individual patient data, dealing with non-standard sets of data, inclusion of trials with different designs, a Bayesian approach to meta-analysis and sequential methods for meta-analysis. The author has published 5 papers based on the work described in these chapters in journals such as Statistics in Medicine. There is ongoing research based on the contents of Chapter 12. Chapters 6-8 on dealing with heterogeneity, presentation and interpretation of results and selection bias mainly present methods which have appeared in the literature by other authors. RAE_import_type : Journal article RAE_uoa_type : Statistics and Operational Research

PY - 2001/8/15

Y1 - 2001/8/15

N2 - Meta-analyses are being undertaken in an increasing diversity of diseases and conditions, some of which involve outcomes measured on an ordered categorical scale. We consider methodology for undertaking a meta-analysis on individual patient data for an ordinal response. The approach is based on the proportional odds model, in which the treatment effect is represented by the log-odds ratio. A general framework is proposed for fixed and random effect models. Tests of the validity of the various assumptions made in the meta-analysis models, such as a global test of the assumption of proportional odds between treatments, are presented. The combination of studies with different definitions or numbers of response categories is discussed. The methods are illustrated on two data sets, in a classical framework using SAS and MLn and in a Bayesian framework using BUGS. The relative merits of the three software packages for such meta-analyses are discussed. Copyright © 2001 John Wiley & Sons, Ltd.

AB - Meta-analyses are being undertaken in an increasing diversity of diseases and conditions, some of which involve outcomes measured on an ordered categorical scale. We consider methodology for undertaking a meta-analysis on individual patient data for an ordinal response. The approach is based on the proportional odds model, in which the treatment effect is represented by the log-odds ratio. A general framework is proposed for fixed and random effect models. Tests of the validity of the various assumptions made in the meta-analysis models, such as a global test of the assumption of proportional odds between treatments, are presented. The combination of studies with different definitions or numbers of response categories is discussed. The methods are illustrated on two data sets, in a classical framework using SAS and MLn and in a Bayesian framework using BUGS. The relative merits of the three software packages for such meta-analyses are discussed. Copyright © 2001 John Wiley & Sons, Ltd.

U2 - 10.1002/sim.919

DO - 10.1002/sim.919

M3 - Journal article

VL - 20

SP - 2243

EP - 2260

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 15

ER -