Correcting for multivariate measurement error by regression calibration in meta-analyses of epidemiological studies

被引：57

作者：

Wood, A. M. ^{[16
]}

White, I. R.

Thompson, S. G.

Kostis, J. B.

Wilson, A. C.

Wu, K.

Benderly, M.

Goldbourt, U.

Willeit, J.

Kiechl, S.

Yarnell, J. W. G.

Sweetnarn, P. M.

Elwood, P. C.

Cushman, M.

Tracy, R. P.

Tybjaerg-Hansen, A. ^{[1
]}

Haverkate, F.

Thompson, S. G.

Lee, A. J. ^{[2
,3
]}

Smith, F. B. ^{[2
,3
]}

Salomaa, V.

Harald, K.

Rasi, V.

Jousilahti, P.

Pekkanen, J.

D'Agostino, R. ^{[4
]}

Wilson, P. W. F. ^{[4
]}

Tofler, G. ^{[4
]}

Levy, D. ^{[4
]}

Marchioli, R.

Valagussa, F.

Rosengren, A. ^{[5
,6
]}

Lappas, G. ^{[5
,6
]}

Eriksson, H. ^{[5
,6
]}

Cremer, P. ^{[7
]}

Nagel, D. ^{[7
]}

Curb, J. D. ^{[8
]}

Rodriguez, B. ^{[8
]}

Yano, K. ^{[8
]}

Salonen, J. T. ^{[9
]}

Nyyssoenen, K. ^{[9
]}

Tuomainen, T. -P. ^{[9
]}

Hedblad, B. ^{[10
]}

Engstroem, G. ^{[10
]}

Berglund, G. ^{[10
]}

Loewel, H. ^{[11
]}

Hense, H. W. ^{[11
]}

Meade, T. W.

Cooper, J. A.

De Stavola, B.

机构：

[1] Copenhagen City Heart Study, Copenhagen, Denmark

[2] Edinburgh Artery Study, Edinburgh, Midlothian, Scotland

[3] Edinburgh Claudicat Study, Edinburgh, Midlothian, Scotland

[4] Framingham Study, Framingham, MA USA

[5] Goteborg 1913 Study, Gothenburg, Sweden

[6] Goteborg 1933 Study, Gothenburg, Sweden

[7] Gottingen Risk Incidence & Prevalence Study, Gottingen, Germany

[8] Honolulu Heart Program, Honolulu, HI USA

[9] Kuopio Ischaem Heart Dis Study, Kuopio, Finland

[10] Malmo Study, Malmo, Sweden

[11] MONICA KORA Augsburg Study, Augsburg, Germany

[12] Osaka Study, Osaka, Japan

[13] Prospect Cardiovasc Munster Study, Munster, Germany

[14] Quebec Cardiovasc Study, Quebec City, PQ, Canada

[15] Vicenza Thrombophilia & Atherosclerosis Project, Vicenza, Italy

[16] Univ Cambridge, Cambridge, England

来源：

STATISTICS IN MEDICINE | 2009年 / 28卷 / 07期

关键词：

measurement error; within-person variation; meta-analysis; individual participant data; regression calibration; CONFIDENCE-INTERVALS; MENDELIAN RANDOMIZATION; HEART-DISEASE; DILUTION; UNDERESTIMATION; VARIABLES; COHORT;

D O I：

10.1002/sim.3530

中图分类号：

Q [生物科学];

学科分类号：

090105 [作物生产系统与生态工程];

摘要：

Within-person variability in measured values of multiple risk factors call bias their associations with disease. The multivariate regression calibration (RC) approach call correct for such measurement error and has been applied to Studies in which true Values or independent repeat measurements of the risk factors are observed oil a subsample. We extend the multivariate RC techniques to a meta-analysis framework where Multiple studies provide independent repeat measurements and information oil disease outcome. We consider the cases where sonic or all studies have repeat measurements, and compare study-specific, averaged and empirical Bayes estimates of RC parameters. Additionally, we allow for binary covariates (e.g. smoking status) and for uncertainty and time trends in the measurement error corrections. Our methods are illustrated using a subset of individual participant data from prospective long-term studies ill the Fibrinogen Studies Collaboration to assess file relationship between usual levels of plasma fibrinogen and the risk of coronary heart disease, allowing for measurement error in plasma fibrinogen and several confounders. Copyright (C) 2009 John Wiley & Soils, Ltd.

引用

页码：1067 / 1092

页数：26

共 37 条

[1]

The Emerging Risk Factors Collaboration: analysis of individual data on lipid, inflammatory and other markers in over 1.1 million participants in 104 prospective studies of cardiovascular diseases [J].