S3E27: Propensity Scores -- I Meant To Do That!
Quantitude
00:00
How to Estimate the Treatment Effect?
The treatment is a mediator between the confounders and t outcome. Of key interest is treatment, condition a mediator? I'm a congenital counter. We're on number two, but you said there were four i'm starging to feel really uncomfortable. Well, talk about theother two. What i see in my mind's eye, is ascetico variats predicting a binary outcome in step one,. In step two, we have the binary predictor of your dependent variable. And so all you're left with this, a variance is due to the treatment. But treating this as mediation is not useful because usually in mediat we have a focal predictor, and then the
Transcript
Play full episode
