The impact of residual and unmeasured confounding in epidemiologic studies: a simulation study.

By Zoe Fewell, George Davey Smith, J. Sterne. American Journal of Epidemiology, 2007

683 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Statistically Controlling for Confounding Constructs Is Harder than You Think (2016, background): “Of course, this general problem is not novel, and has been discussed in a number of literatures [8–10]—most extensively, under the heading of “residual confounding” in epidemiology [3,5].”
Exploring pathways linking greenspace to health: Theoretical and methodological guidance (2017, result): “It is reassuring that the likely impact of unmeasured confounders is often small and would only substantially bias the results if it was not correlated with other measured confounders (Fewell et al., 2007).”
Inflation of Type I error rate in multiple regression when independent variables are measured with error (2009, methodology): “For linear models with measurement error, we prefer to use classical structural equation modelling of the kind described by Jöreskog (1978) andBollen (1989), rather than, for example, the arguably more sophisticated methods of Fuller (1987).”