you trust random figures on the internet too much
-
-
-
are they wrong
-
sample sizes too small so yes
-
on one hand that seems like a plausible problem, on the other hand the effect size is enormous and seems likely to swamp n-related noise
-
http://andrewgelman.com/2017/02/06/not-kill-statistical-significance-makes-stronger-fallacy/ … you need much more Gelman in your life
-
you're preaching to the choir but you're applying the gospel to the wrong case this is just a simple issue of estimating a simple population moment they certainly have enough power to identify three-fold changes in level across years
-
For the time series figures, you don’t get curves those smooth with very high n. For the antidepressant chart, ofc we have those rates.
-
Oh yikes I thought you were referring to the figures earlier in the thread that used the GSS. I was wrong.
- 1 more reply
New conversation -
-
-
Maybe the real miracle is the drug, alcohol, and suicide related mortality we made along the way
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.