There is no good definition of probability. For frequentists, it requires an infinite number of independent events, i.e., it doesn’t exist in the real world. For Bayesians, it’s subjective, i.e., arbitrary and useless for science.
-
Bayesianism isnt useless for science, its the closest thing we have to a formal definition of the scientific process. Bayesianism is theoretically optimal, as proven by Solomonoff in his theory of inductive inference.https://en.m.wikipedia.org/wiki/Solomonoff%27s_theory_of_inductive_inference …
-
-
Science is reliant upon its priors as much as anything else. There’s fundamentally no way around the fact that rationality is inherently relative to our frame of reference
-
Priors do not imply subjectivity.
Keskustelun loppu
Uusi keskustelu -
-
-
Rationality is not a particular set of beliefs. Rationality is a method for updating our beliefs when we get new information. The subjectivity in Bayesianism is nothing more than the fundamental uncertainty that can never be eliminated, only reduced
-
That’s how Bayesians try to define away their shortcomings.
- Näytä vastaukset
Uusi keskustelu -
Lataaminen näyttää kestävän hetken.
Twitter saattaa olla ruuhkautunut tai ongelma on muuten hetkellinen. Yritä uudelleen tai käy Twitterin tilasivulla saadaksesi lisätietoja.