Carl Gold, PhDMy PR to the #EconML #PyWhy #opensource #causalai project was merged! 🎉 I made a small contribution by allowing a flexible choice of evaluation metric for scoring both the first stage and final stage models in Double Machine Learning (#DML). Before, only the mean square error (MSE) was implemented. But as an ML practitioner "in the trenches" I have found that MSE is hard to interpret and compare across models. My new functions allow that 🙂 #CausalInference #machinelearning #datascience
Matthew MartinNext time someone says, "correlation isn't causation" I now can say, "didn't you keep reading in the stats textbook? The part about causal inference?"
Anyhow, the justifications remind me of Bayesian statistics, where you take prior knowledge and that allows you to say and test something more than "associations do/don't exist" #pywhy
https://www.youtube.com/results?search_query=causal+inference+pywhy
Ken Koon Wong