Gene-environment hypothesis again fails in meta-analysis. Prior for these kinds of claims should be taken as LOW. n = https://www.biologicalpsychiatryjournal.com/article/S0006-3223(17)31993-5/pdf …pic.twitter.com/CRig9ewGs0
-
Just so happens that I did a yuuuge study on that by looking at general importance of interaction effects across randomly chosen triplets of variables in a large dataset. Didn't analyze in detail yet, but generally interactions are usually not large/important.
Given that, this means that they are generally hard to detect with the usual small sample sizes in social science, and thus if detected by usual standard of p < .05 (with QRP), will generate fail to replicate. I need someone to collab with to finish this study.
