期刊名称：Epidemiology, Biostatistics and Public Health
印刷版ISSN：2282-0930
出版年度：2013
卷号：10
期号：1
DOI：10.2427/8757
语种：English
出版社：PREX
摘要：A common aim of epidemiological research is to estimate the causal effect of a particular exposure on a particular outcome. Towards this end, observed associations are often ‘adjusted’ for potential confounding variables. When the potential confounders are unmeasured, explicit adjustment becomes unfeasible. It has been demonstrated that causal effects can be estimated even in the presence of umeasured confounding, utilizing a method called ‘front-door blocking’. In this paper we generalize this method to longitudinal studies. We demonstrate that the method of front-door blocking poses a number of challenging statistical problems, analogous to the famous problems associ- ated with the method of ‘back-door blocking’.
