@article{3112159,
    title = "Statistical methods for the time-to-event analysis of individual participant data from multiple epidemiological studies",
    author = "Thompson, S. and Kaptoge, S. and White, I. and Wood, A. and Perry, P. and Danesh, J. and The Emerging Risk Factors Collaboration and Thompson, S.G. and Kaptoge, S. and White, I.R. and Wood, A.M. and Perry, P.L. and Tipping, R.W. and Ford, C.E. and Simpson, L.M. and Walldius, G. and Jungner, I. and Chambless, L.E. and Panagiotakos, D.B. and Pitsavos, C. and Chrysohoou, C. and Stefanadis, C. and Knuiman, M. and Goldbourt, U. and Benderly, M. and Tanne, D. and Whincup, P.H. and Wannamethee, S.G. and Morris, R.W. and Willeit, J. and Kiechl, S. and Santer, P. and Mayr, A. and Lawlor, D.A. and Yarnell, J.W.G. and Gallacher, J. and Casiglia, E. and Tikhonoff, V. and Nietert, P.J. and Sutherland, S.E. and Bachman, D.L. and Keil, J.E. and Cushman, M. and Tracy, R.P. and Tybjærg-Hansen, A. and Nordestgaard, B.G. and Benn, M. and Frikke- Schmidt, R. and Giampaoli, S. and Palmieri, L. and Panico, S. and Vanuzzo, D. and Gómez de la Cámara, A. and Gómez- Gerique, J.A. and Simons, L. and McCallum, J. and Friedlander, Y. and Fowkes, F.G.R. and Lee, A.J. and Taylor, J. and Guralnik, J.M. and Wallace, R. and Guralnik, J. and Blazer, D.G. and Guralnik, J.M. and Guralnik, J.M. and Khaw, K.-T. and Brenner, H. and Raum, E. and Müller, H. and Rothenbacher, D. and Jansson, J.H. and Wennberg, P. and Nissinen, A. and Donfrancesco, C. and Salomaa, V. and Harald, K. and Jousilahti, P. and Vartiainen, E. and Woodward, M. and D'Agostino, R.B. and Vasan, R.S. and Pencina, M.J. and Bladbjerg, E.M. and Jørgensen, T. and Jespersen, J. and Møller, L. and Dankner, R. and Chetrit, A. and Lubin, F. and Rosengren, A. and Lappas, G. and Björkelund, C. and Lissner, L. and Bengtsson, C. and Cremer, P. and Nagel, D. and Tilvis, R.S. and Strandberg, T.E. and Kiyohara, Y. and Arima, H. and Doi, Y. and Ninomiya, T. and Rodriguez, B. and Dekker, J.M. and Nijpels, G. and Stehouwer, C.D.A. and Rimm, E. and Pai, J.K. and Sato, S. and Kitamura, A. and Iso, H. and Goldbourt, U. and Noda, H. and Harald, K. and Jousilahti, P. and Vartiainen, E. and Salonen, J.T. and Tuomainen, T.-P. and Deeg, D.J.H. and Poppelaars, J.L. and Meade, T.W. and Cooper, J.A. and Hedblad, B. and Berglund, G. and Engstrom, G. and Verschuren, W.M.M. and Blokstra, A. and Cushman, M. and Shea, S. and Döring, A. and Koenig, W. and Meisinger, C. and Mraz, W. and Bas Bueno-de-Mesquita, H. and Kuller, L.H. and Grandits, G. and Selmer, R. and Tverdal, A. and Nystad, W. and Gillum, R. and Mussolino, M. and Rimm, E. and Manson, J.E. and Pai, J.K. and Meade, T.W. and Cooper, J.A. and Cooper, J.A. and Knottenbelt, C. and Bauer, K.A. and Naito, Y. and Holme, I. and Hankinson, S. and Tverdal, A. and Nystad, W. and Nakagawa, H. and Miura, K. and Ducimetiere, P. and Jouven, X. and Crespo, C.J. and Garcia Palmieri, M.R. and Amouyel, P. and Arveiler, D. and Evans, A. and Ferrieres, J. and Schulte, H. and Assmann, G. and Shepherd, J. and Packard, C.J. and Sattar, N. and Ford, I. and Cantin, B. and Després, J.-P. and Dagenais, G.R. and Barrett-Connor, E. and Wingard, D.L. and Bettencourt, R. and Gudnason, V. and Aspelund, T. and Sigurdsson, G. and Thorsson, B. and Trevisan, M. and Witteman, J. and Kardys, I. and Breteler, M. and Hofman, A. and Tunstall-Pedoe, H. and Tavendale, R. and Lowe, G.D.O. and Ben-Shlomo, Y. and Howard, B.V. and Zhang, Y. and Umans, J. and Onat, A. and Davey-Smith, G. and Wilsgaard, T. and Ingelsson, E. and Lind, L. and Giedraitis, V. and Lannfelt, L. and Gaziano, J.M. and Ridker, P. and Gaziano, J.M. and Ridker, P. and Ulmer, H. and Diem, G. and Concin, H. and Tosetto, A. and Rodeghiero, F. and Wassertheil-Smoller, S. and Manson, J.E. and Marmot, M. and Clarke, R. and Collins, R. and Brunner, E. and Shipley, M. and Ridker, P. and Buring, J. and Shepherd, J. and Cobbe, S.M. and Robertson, M. and He, Y. and Marín Ibañez, A. and Feskens, E.J.M. and Kromhout, D. and Collins, R. and Di Angelantonio, E. and Erqou, S. and Kaptoge, S. and Lewington, S. and Orfei, L. and Pennells, L. and Perry, P.L. and Ray, K.K. and Sarwar, N. and Alexander, M. and Thompson, A. and Thompson, S.G. and Walker, M. and Watson, S. and Wensley, F. and White, I.R. and Wood, A.M.",
    journal = "International Journal of Epidemiology",
    year = "2010",
    volume = "39",
    number = "5",
    pages = "1345-1359",
    publisher = "Oxford University Press",
    issn = "0300-5771, 1464-3685",
    doi = "10.1093/ije/dyq063",
    keywords = "cholesterol;  fibrinogen, assessment method;  cardiovascular disease;  data set;  epidemiology;  error analysis;  measurement method;  meta-analysis;  occupational exposure;  participatory approach;  regression analysis;  risk factor, article;  body mass;  cardiovascular disease;  cholesterol blood level;  epidemiological data;  ischemic heart disease;  priority journal;  proportional hazards model;  risk factor;  sex difference;  smoking habit;  statistical analysis;  systolic blood pressure",
    abstract = "Background Meta-analysis of individual participant time-to-event data from multiple prospective epidemiological studies enables detailed investigation of exposure-risk relationships, but involves a number of analytical challenges. Methods This article describes statistical approaches adopted in the Emerging Risk Factors Collaboration, in which primary data from more than 1 million participants in more than 100 prospective studies have been collated to enable detailed analyses of various risk markers in relation to incident cardiovascular disease outcomes. Results Analyses have been principally based on Cox proportional hazards regression models stratified by sex, undertaken in each study separately. Estimates of exposure-risk relationships, initially unadjusted and then adjusted for several confounders, have been combined over studies using meta-analysis. Methods for assessing the shape of exposure-risk associations and the proportional hazards assumption have been developed. Estimates of interactions have also been combined using meta-analysis, keeping separate within-and between-study information. Regression dilution bias caused by measurement error and within-person variation in exposures and confounders has been addressed through the analysis of repeat measurements to estimate corrected regression coefficients. These methods are exemplified by analysis of plasma fibrinogen and risk of coronary heart disease, and Stata code is made available. Conclusion Increasing numbers of meta-analyses of individual participant data from observational data are being conducted to enhance the statistical power and detail of epidemiological studies. The statistical methods developed here can be used to address the needs of such analyses. © The Author 2010; all rights reserved."
}