CMStatistics 2021: Start Registration
View Submission - CMStatistics
B0902
Title: Disentangling confounding and nonsense associations due to dependence Authors:  Elizabeth Ogburn - Johns Hopkins University (United States) [presenting]
Abstract: Nonsense associations can arise when an exposure and an outcome of interest exhibit similar patterns of dependence. Confounding is present when potential outcomes are not independent of treatment. How confusion about these two phenomena underpins popular methods in three areas will be described: causal inference with multiple treatments and unmeasured confounding; causal and statistical inference with social network data; and statistical genetics methods for dealing with unmeasured confounding.