My prior for this hp is very strong. You can compare n with dfs for interactions - not sure how robust the automated method would be tho. The only way is to manually code a bunch of papers
@MicheleNuijten When noting p values etc. from literature, do you also note whether they are reported interactions or not? My hypothesis is that findings for interactions are particularly low reliability due to lower prior and less power wrt. sample size.
-
-
-
To clarify, h1: interactions are more likely to be false positive compared to main effects. In p-values, they are more likely to have p value incorrectly rounded
End of conversation
New conversation -
-
-
We were planning to look into this, but the project lost momentum. We didn't code any types of test manually, but you should be able to go a long way with the dfs
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.