The study specifically controlled to find causationhttps://twitter.com/brobrahbrehbro/status/1142592617391120384 …
Nope. Longitudinal studies can't reveal causation unless they do random assignment or include twin/family design that can control for genetic confounds.
-
-
The study followed individuals for over 20 years, testing their IQ at 13, and then in their 30s
-
Yes. But longitudinal studies by themselves cannot show causation. Bad study design + low power + no genetic controls + no randomization = no scientific value.
- 1 more reply
New conversation -
-
-
Appreciating the power of a study in its context and putting it in proper perspective is an art in itself. I find the results of the study fascinating, would love for their to be a more robust version of it, the case is by no means closed, but this does give cause for concern...
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Wouldn’t this problem be sorted by controlling for school performance and socioeconomic conditions prior to high-school, and socioeconomic conditions through high-school?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Stefan Molyneux does not understand the scientific method or statistics. He's a good speaker but has very few deep insights.
-
Agreed. He clearly has no understanding of causation. Good thing not everyone on twitter is in his cult.
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.