Examples Using Tree-Based Analysis
In epidemiologic studies, one of the most frequently encountered issues is to evaluate the association between a set of putative risk factors and a disease outcome, controlling for another set of potential confounders. In this chapter, we illustrate how to apply the tree-based method in this regard. The discussion is mostly adopted from Zhang and Bracken (1996).
KeywordsBirth Control Linear Discriminant Analysis Spontaneous Abortion Terminal Node Adjusted Relative Risk
Unable to display preview. Download preview PDF.
- N. Mantel and W. Haenszel. Statistical aspects of the analysis of data from retrospective studies of disease. Journal of the National Cancer Institute, 22:719–748, 1959.Google Scholar
- O.S. Miettinen. Stratification by a multivariate confounder score. American Journal of Epidemiology, 104:609–620, 1976.Google Scholar
- P.K. Mills, W.L. Beeson, R.L. Phillips, and G.E. Fraser. Bladder cancer in a low risk population: results from the Adventist Health Study. American Journal of Epidemiology, 133:230–239, 1991.Google Scholar
- H.P. Zhang and M.B. Bracken. Tree-based, two-stage risk factor analysis for spontaneous abortion. American Journal of Epidemiology, 144:989–996, 1996.Google Scholar
- A. Asuncion and D.J. Newman. UCI Machine Learning Repository. [http://www.ics.uci.edu/~mlearn/MLRepository.html], University of California, School of Information and Computer Sciences, Irvine, CA, 2007.