Bias attenuation results for nondifferentially mismeasured ordinal and coarsened confounders
Suppose we are interested in the effect of a binary treatment on an outcome where that relationship is confounded by an ordinal confounder. We assume that the true confounder is not observed but, rather, we observe a nondifferentially mismeasured version of it. We show that, under certain monotonicity assumptions about its effect on the treatment and on the outcome, an effect measure controlling for the mismeasured confounder will fall between the corresponding crude and true effect measures. We also present results for coarsened and, under further assumptions, multiple misclassified confounders. Copyright 2013, Oxford University Press.
Year of publication: |
2013
|
---|---|
Authors: | Ogburn, Elizabeth L. ; Vanderweele, Tyler J. |
Published in: |
Biometrika. - Biometrika Trust, ISSN 0006-3444. - Vol. 100.2013, 1, p. 241-248
|
Publisher: |
Biometrika Trust |
Saved in:
Online Resource
Saved in favorites
Similar items by person
-
Why and When "Flawed" Social Network Analyses Still Yield Valid Tests of no Contagion
VanderWeele, Tyler J., (2012)
-
Causal inference, social networks and chain graphs
Ogburn, Elizabeth L., (2020)
-
The Magnitude and Direction of Collider Bias for Binary Variables
Nguyen, Trang Quynh, (2019)
- More ...