So trying to do some #GCTA meta-analysis for intelligence/cognitive traits, and the estimates *decrease* with age‽pic.twitter.com/RuM129w6Ow
-
@gwern p=0.009 & I^2=0 with `~ Age.mean`. But heritability is supposed to increase with age so why aren't the GCTAs...
@gwern Good question. Despite p=.009, I judge 90% it is a fluke. I'll write down my prediction.
-
-
@KirkegaardEmil Thought it might be rich-twin-samples~>higher-heritability, but coded up twin as covariate; non-significant & negative-sign. -
@KirkegaardEmil You know what, I bet it's due to no adult/middle-aged samples: datapoints jump from 14yo to 57yo, hiding any quadratic hump. -
@gwern Or just a fluke. Flukes are common in moderator analyses. Let's see if the next study confirms the pattern. What about the missing?
End of conversation
New conversation -
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.