Oh man, this is a wonderfully silly headline. Just one point from the study - eating chocolate did not 'significantly' increase weight, but it did increase calorie intake by ~200-300kcal per day over the 14 days of the studyhttps://twitter.com/CaulfieldTim/status/1409566065021968384 …
-
-
Also also, this appears to be a post-hoc power calculation justifying the sample size, which I'm sure will please
@ADAlthousePhD immenselypic.twitter.com/hfCVhDX2t2
Show this thread -
Another point - while the differences may have been statistically significant on ANOVA, I calculated Cohen's d for the difference between activity and it's around 0.15, representing an increase in ~4 mins activity a day associated with eating chocolatepic.twitter.com/8x21fo8cCn
Show this thread
End of conversation
New conversation -
-
-
So basically lesson here is, to get a desired "no significant X", just keep N small and you'll make the newspapers?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
20 comparisons so at p = .05 expect 1/20 to be different by chance alone. Yes?
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.