@semiotechnic Once you start saying X *more* likely than Y, you are quantifying. Seems unavoidable common sense.
-
-
Replying to @simplic10
@simplic10@semiotechnic ...cardinal model supporting any given ordinal quantification, but it's not clear whether you'd gain any info.3 replies 0 retweets 0 likes -
Replying to @St_Rev
@St_Rev@semiotechnic >... if you choose Red Sox, seems to imply you think Red Sox victory has prob > 1/20 M.2 replies 0 retweets 0 likes -
Replying to @simplic10
@simplic10@semiotechnic ...but I don't think that implies that P(red sox victory) is quantifiable.2 replies 0 retweets 0 likes -
Replying to @St_Rev
@St_Rev@semiotechnic P(Red Sox Victory) is BOTH non-quantifiable AND has prob greater than 1/20M?1 reply 0 retweets 0 likes -
Replying to @simplic10
@simplic10@semiotechnic Yes. You're mistaking abuse of notation for proof. Here P and > are shorthand for looser concepts of likelihood.9 replies 0 retweets 0 likes -
Replying to @St_Rev
@St_Rev@semiotechnic My point is you can "sandwich" P(RedSoxVic) between two classic lottery probabilities... odd to say incommensurate.2 replies 0 retweets 0 likes -
Replying to @simplic10
@simplic10@semiotechnic I distinguished earlier between ordinal and cardinal likelihood. Compare to utility theory. To say u(X) > u(Y)...1 reply 0 retweets 0 likes -
Replying to @St_Rev
@St_Rev@semiotechnic What I find odd is that you are willing to say "a > X > b" but also "X is a completely different thing from a & c."3 replies 0 retweets 0 likes -
Replying to @simplic10
@simplic10@semiotechnic Or, more elaborately, 0 < D < 1 where D is a bump distribution supported on (0.2, 0.8).1 reply 0 retweets 0 likes
@St_Rev @simplic10 @semiotechnic Or: "somewhat likely" > .0001 but is not equivalent to any specific formulation.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.