There are a lot more comparisons of correlation vs causation in the lit: https://www.gwern.net/Correlation Benson is right there's no consistent bias; the problem is that estimates differ drastically and examining overlapping CIs is typically just plain underpowered a test.
How's this for heterodox viewpoint? Though the comeback is that maybe the RCT evidence is just biased due to pub bias. http://www.nejm.org/doi/full/10.1056/NEJM200006223422506 …pic.twitter.com/M0pi7OWVSa
-
-
-
Which is why my suggested conceptualization is to treat it as a mixture model and ask how often the randomized effect sizes are drawn from a different (much narrower) distribution...
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.