@KirkegaardEmil I don't see adhoc.r in the repo. If OLS is biased, why not use polr or glm with link functions like poisson or binomial?
Cognitive dysgenics in the OKCupid dataset: a few simple analyses http://emilkirkegaard.dk/en/?p=5942 pic.twitter.com/bW384lcfo0
-
-
-
@gwern I said "simple analyses". ;) I don't have any exp with modeling ordinals. I forgot to upload that file. https://osf.io/gk7b3/ -
@KirkegaardEmil Why do you do glms with binomials in the middle but then revert to regular lm/gaussian at the bottom? -
@gwern Cuz i don't know the function for ordinal outcomes, but I know latent r's for bi-variate, so that's why. ;)
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.