wedrifid comments on Rational Romantic Relationships, Part 1: Relationship Styles and Attraction Basics - Less Wrong

48 Post author: lukeprog 05 November 2011 11:06AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (1529)

You are viewing a single comment's thread. Show more comments above.

Comment author: wedrifid 10 November 2011 08:26:13AM 0 points [-]

As I said, I'm less interested in "scientific" evidence than Bayesian evidence. The latter can be disappointingly orthogonal to the former, in that what's generally good scientific evidence isn't always good Bayesian evidence, and good Bayesian evidence isn't always considered scientific.

What are some examples of good scientific evidence that isn't good bayesian evidence?

Comment author: pjeby 10 November 2011 05:42:50PM 0 points [-]

What are some examples of good scientific evidence that isn't good bayesian evidence?

Uh, how about all of parapsychology, aka "the control group for the scientific method". ;-) Psi experiments can reach p .05 under conventional methods without being good Bayesian evidence, as we've seen recently with that "future priming" psi experiment.

(Note that I said "scientific" not Scientific. ;-) )

Comment author: wedrifid 10 November 2011 05:57:32PM 1 point [-]

Ok, I wouldn't have necessarily classed that as 'good scientific evidence' but it seems to be useful Bayesian evidence so we must be looking at it from different angles.