Fig. 4From: The alarming problems of confounding equivalence using logistic regression models in the perspective of causal diagramsScenario 2 (Fig. 1b), simulation results of the bias (a and b) and standard error (c and d) of c-equivalence sets B 1 ≈ B 2 when varied across the log transformed odds ratio effect of T on Y and W on Y Back to article page