3 Comments
User's avatar
Cosma's avatar

Since you liked the last comment: I hope someone smarter than me (like yourself!) will resolve these related quandries for me: [http://bactra.org/notebooks/clinical-vs-actuarial.html]

Expand full comment
Ben Recht's avatar

I have so many thoughts about this. But I haven't read Meehl's argument that "there are no known cases where clinicians reliably out-perform actuarial methods."

I did a quick read of the links at the bottom of your blog, and I think that Meehl is arguing this is true specifically in clinical psychology. I wonder if he thinks this is true more broadly. I know many examples where it is decidedly not true in medicine: Morgenstern's article details lots of examples, and the same is true in cancer diagnostics and other statistical screening methods.

Let me do some reading before commenting further. Like you, I'm fascinated by the conundrum.

Expand full comment
Maxim Raginsky's avatar

I was hoping someone (you) would bring this up so I didn’t have to.

Expand full comment