Closed athulsudheesh closed 3 weeks ago
I found the answer myself. The ATE reported by dowhy while using a logistic regression is sometimes called as the risk difference (in social and medical sciences). This article was helpful for me to understand the theory behind the ATE estimation: https://solomonkurz.netlify.app/blog/2023-04-24-causal-inference-with-logistic-regression/ There are formulas one can find in the literature to convert the risk difference to cohen's d (which is the standard measure used in psych sciences).
How is the mean (which is the reported effect by the package) computed while using logistic regression for estimating causal effect in dowhy? Is the reported effect in cohen's d or odds ratio?