Emil O W Kirkegaard

worth adding that significant variables aren’t automatically good for understanding either http://jakewestfall.org/publications/ivy.pdf …https://twitter.com/russpoldrack/status/664496223395557376 …

@talyarkoni Good that someone wrote about that problem. I had also noticed it before, but never wrote anything about it.

@KirkegaardEmil epidemiologists call it “residual confounding" (see our paper for refs), but hasn’t been discussed in psychology @CookieSci

@talyarkoni @CookieSci The implication for discriminant validity analysis is probably one of the reasons for rampant construct proliferation