If psychologists had to present and defend a DAG every time they did a mediation analysis, 10% of them would result in "sorry the effect we care about isn't identified" and the other 90% would be "sorry we don't understand this phenomenon well enough to draw a DAG"
(Apparently today is "be salty about mediation" day in my brain)
Real talk though, I think mediation analysis can sometimes be useful if it comes with a thorough, eyes-open discussion of all the things that must be true for it to be interpretable as mediation
It's just that that hardly ever happens
• • •
Missing some Tweet in this thread? You can try to
force a refresh
