https://slatestarcodex.com/2019/05/07/5-httlpr-a-pointed-review/ … Psychiatry researchers published hundreds of papers about something that didn't exist. This is why I'm such a killjoy about correlational evidence; nearly all of the (false) results mentioned here were correlational.
-
-
Replying to @s_r_constantin
More emphasis on causal analysis, esp. as some tools are becoming available?
1 reply 0 retweets 0 likes -
Replying to @nlpnyc
Sure, but I don't have a prescription for researchers as much as for *readers* of research. If you see a correlational study finding a gene "modulates" a phenotype, and it isn't huge, or doesn't control for multiple comparisons, try to erase it from your memory!
1 reply 0 retweets 1 like -
Replying to @s_r_constantin @nlpnyc
Also: if you see an fMRI study (as some of these were), IMMEDIATELY erase it from your memory; fMRI finds "neural activity" in dead fish!
1 reply 0 retweets 0 likes
People tend to read replication-crisis stories like this and take away the message "oh no, everything we thought was safe is actually uncertain!" when actually the message is "don't believe claims supported by evidence you know damn well is sketchy."
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.