factual

Comparing likelihoods needs no priors

To judge which of two experiments (e.g., to detect a WIMP versus to exclude an axion as dark matter) is more useful, you need only compare the likelihoods—how probable the evidence would be under each hypothesis—not the priors, because the likelihood comparison reveals whether and in which direction the evidence favors one hypothesis, even though determining the resulting probabilities would still require priors.

factualpending

Speaker

Branden Fitelson

Evidence Quote

“that will give you some information about the relevance dimension. Like does the evidence favor one over the other? It may not tell you the probabilities 'cause for that you're going to need priors.”

Source

315 | Branden Fitelson on the Logic and Use of Probability— Sean Carroll's Mindscape
Created: 6/13/2026, 12:14:37 AM

Your notes

Loading notes...