Bounding Formulas for Selection Bias

Tzu-Hsuan Huang, Wen-Chung Lee
2015 American Journal of Epidemiology  
Researchers conducting observational studies need to consider 3 types of biases: selection bias, information bias, and confounding bias. A whole arsenal of statistical tools can be used to deal with information and confounding biases. However, methods for addressing selection bias and unmeasured confounding are less developed. In this paper, we propose general bounding formulas for bias, including selection bias and unmeasured confounding. This should help researchers make more prudent
more » ... re prudent interpretations of their (potentially biased) results. confounding; effect modification; epidemiologic methods; selection bias Abbreviations: COR, confounding odds ratio; OR, odds ratio; SOR, standardized odds ratio.
doi:10.1093/aje/kwv130 pmid:26519426 fatcat:zt4a7l7tenbcjitfx25whcfvzm