Extension of the modified Poisson regression model to prospective studies with correlated binary data

Statistical Methods in Medical Research - Tập 22 Số 6 - Trang 661-670 - 2013
Guangyong Zou1, Allan Donner1
1Department of Epidemiology & Biostatistics, and Robarts Clinical Trials of Robarts Research Institute, Schulich School of Medicine & Dentistry, University of Western Ontario, London, Ontario, Canada

Tóm tắt

The Poisson regression model using a sandwich variance estimator has become a viable alternative to the logistic regression model for the analysis of prospective studies with independent binary outcomes. The primary advantage of this approach is that it readily provides covariate-adjusted risk ratios and associated standard errors. In this article, the model is extended to studies with correlated binary outcomes as arise in longitudinal or cluster randomization studies. The key step involves a cluster-level grouping strategy for the computation of the middle term in the sandwich estimator. For a single binary exposure variable without covariate adjustment, this approach results in risk ratio estimates and standard errors that are identical to those found in the survey sampling literature. Simulation results suggest that it is reliable for studies with correlated binary data, provided the total number of clusters is at least 50. Data from observational and cluster randomized studies are used to illustrate the methods.

Từ khóa


Tài liệu tham khảo

Huber P, 1967, In: Le Cam LM and Neyman J (eds) Proceedings of the fifth berkeley symposium on mathematical statistics and probability, 1, 221

10.1093/aje/kwh090

10.1093/oxfordjournals.aje.a114593

10.1016/S0197-2456(97)00147-5

10.1016/j.cct.2006.08.007

10.1214/08-STS262

10.1016/0895-4356(91)90203-L

10.1002/sim.3751

10.1093/oxfordjournals.aje.a114212

10.1093/biostatistics/kxh016

Yelland LN, 2011, Int J Biostat, 7

10.1093/biostatistics/kxr030

10.1016/j.jclinepi.2006.12.001

10.1016/0021-9681(81)90040-0

10.1016/0021-9681(87)90106-8

10.1002/sim.4780141907

10.1093/biomet/73.1.13

10.1093/oxfordjournals.aje.a113261

Donner A, 2000, Design and analysis of cluster randomization trials in health research

Hardin JW. The sandwich estimate of variance. In: Fomby TB and Hill RC (eds) Maximum likelihood estimation of misspecified models: twenty years later. Advances in econometrics. Vol. 17, Bingley, UK: Emerald Group Publishing Limited, 2003, pp. 45–73.

Cochran WG. Sampling techniques, 3rd edn. New York: Wiley, 1973, pp. 30–67.

10.1093/aje/kwf215

10.1111/j.0006-341X.2001.00126.x

10.1093/oxfordjournals.aje.a009511

10.1093/biomet/85.2.487

10.1111/j.0006-341X.1999.00574.x

10.1161/HYPERTENSIONAHA.108.123455

10.1093/aje/kwi188

10.1177/1740774506075667

10.1177/0962280206071931

Campbell MJ, Relative Risks, Odds Ratios and Cluster Randomised Trials

10.1186/1471-2288-8-80

10.1093/aje/kwp015

10.1016/j.csda.2007.04.020