Methods for Analyzing Secondary Outcomes in Public Health Case–Control Studies
Case–control studies are common in public health research. In these studies, cases are chosen based on the primary outcome but there are usually many other related variables which are collected. While the analysis of the association between the primary outcome and exposure variables is generally the main focus of the study, the association between secondary outcomes and exposure variables may also be of interest. Since the experiment was designed for the analysis of the primary outcome, the analysis of secondary outcomes may suffer from selection bias. In this chapter we will introduce the problem and the potential biased inference that can result from ignoring the sampling design. We will discuss and compare a design-based and model-based approach to account for the bias, and demonstrate the methods using a public health data set.
KeywordsSecondary Outcome Propensity Score Smoking Behavior Propensity Score Match Inverse Probability Weighting
The authors wish to thank Dr. David C. Christiani for generously sharing his data. This research was supported in part by the National Institute of Mental Health, Award Number K01MH087219. The content of this paper is solely the responsibility of the authors, and it does not represent the official views of the National Institute of Mental Health or the National Institutes of Health.
- Amos, C.I., Wu, X., Broderick, P., Gorlov, I.P., Gu, J., Eisen, T., Dong, Q., Zhang, Q., Gu, X., Vijayakrishnan, J., Sullivan, K., Matakidou, A., Wang, Y., Mills, G., Doheny, K., Tsai, Y.Y., Chen, W.V., Shete, S., Spitz, M.R., Houlston, R.S.: Genome-wide association scan of tag SNPs identifies a susceptibility locus for lung cancer at 15q25.1. Nat. Genet. 40(5), 616–622 (2008)Google Scholar
- Ho, D.E., Imai, K., King, G., Stuart, E.A.: MatchIt: nonparametric preprocessing for parametric causal inference. J. Stat. Softw. 42(8), 1–28 (2011). http://www.jstatsoft.org/v42/i08/
- Højsgaard, S., Halekoh, U., Yan, J.: The R package geepack for generalized estimating equations. J. Stat. Softw. 15(2), 1–11 (2005)Google Scholar
- Lettre, G., Jackson, A.U., Gieger, C., Schumacher, F.R., Berndt, S.I., Sanna, S., Eyheramendy, S., Voight, B.F., Butler, J.L., Guiducci, C., Illig, T., Hackett, R., Heid, I.M., Jacobs, K.B., Lyssenko, V., Uda, M., Boehnke, M., Chanock, S.J., Groop, L.C., Hu, F.B., Isomaa, B., Kraft, P., Peltonen, L., Salomaa, V., Schlessinger, D., Hunter, D.J., Hayes, R.B., Abecasis, G.R., Wichmann, H.E., Mohlke, K.L., Hirschhorn, J.N.: Identification of ten loci associated with height highlights new biological pathways in human growth. Nat. Genet. 40(5), 584–591 (2008)CrossRefGoogle Scholar
- Lin, D.Y., Zeng, D.: Proper analysis of secondary phenotype data in case-control association studies. Genet. Epidemiol. 33(3), 356–365 (2009)Google Scholar
- R Core Team: R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria (2014). http://www.R-project.org/
- Sanna, S., Jackson, A.U., Nagaraja, R., Willer, C.J., Chen, W.M., Bonnycastle, L.L., Shen, H., Timpson, N., Lettre, G., Usala, G., Chines, P.S., Stringham, H.M., Scott, L.J., Dei, M., Lai, S., Albai, G., Crisponi, L., Naitza, S., Doheny, K.F., Pugh, E.W., Ben-Shlomo, Y., Ebrahim, S., Lawlor, D.A., Bergman, R.N., Watanabe, R.M., Uda, M., Tuomilehto, J., Coresh, J., Hirschhorn, J.N., Shuldiner, A.R., Schlessinger, D., Collins, F.S., Davey Smith, G., Boerwinkle, E., Cao, A., Boehnke, M., Abecasis, G.R., Mohlke, K.L.: Common variants in the GDF5-UQCC region are associated with variation in human height. Nat. Genet. 40(2), 198–203 (2008)CrossRefGoogle Scholar
- VanderWeele, T.J., Asomaning, K., Tchetgen Tchetgen, E.J., Han, Y., Spitz, M.R., Shete, S., Wu, X., Gaborieau, V., Wang, Y., McLaughlin, J., Hung, R.J., Brennan, P., Amos, C.I., Christiani, D.C., Lin, X.: Genetic variants on 15q25.1, smoking, and lung cancer: an assessment of mediation and interaction. Am. J. Epidemiol. 175(10), 1013–1020 (2012)Google Scholar