On Mon, Aug 15, 2022 at 2:20 AM Alan Grayson <[email protected]> wrote:
> Since we have zero information whether the guy is lying or not, we have to > assume a 50% probability that he's telling the truth. Is there any > "scientist" here willing to go that far? AG > > On Thursday, August 4, 2022 at 3:45:43 PM UTC-6 Alan Grayson wrote: > >> https://www.youtube.com/watch?v=Xk0INH_DI1M >> > > For any binary claim without evidence either way, I think it is reasonable to assign a "prior probability <https://www.analyticsvidhya.com/blog/2021/01/a-beginners-guide-bayesian-inference/>" to 50% when doing Bayesian inference. Though I am not sure this case would be simply: he's lying vs. he's telling the truth. You might also have to consider possibilities such as, he is telling the truth but he is misremembering, or was purposely deceived about the true nature of the events, etc. As one then factors in additional evidence to update the probability estimation, other hypotheses should converge towards 0% while one converges towards 100%. However, with a lack of evidence to add and update our probability estimation, we are stuck with something like 50/50, or 25/25/25/25, without a way to progress any further. Jason -- You received this message because you are subscribed to the Google Groups "Everything List" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/everything-list/CA%2BBCJUiioG94CBio%3D88Vx7NjThhjZpnu4DNG0fFwh4RVwSzqqQ%40mail.gmail.com.
