I just read about what causal forests actually are and I am blown away by how simple it is conceptually. Roughly, just do a random forest, but instead of splitting groups to maximize diffs in Y, maximize diffs in \bar{Y_1}-\bar{Y_0}. Done.
-
Show this thread
-
Of course the details are much more thorny than that. thx
@eigenrobot for reminding me I'd been meaning to look into this. I found this link pretty accessible:https://www.markhw.com/blog/causalforestintro …2 replies 5 retweets 54 likesShow this thread
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.