It’s hard to determine how likely it is I’m not high and staring at a bunch of skittles or something that I mistakenly think is a good argument, as Yvain has said.
I’m thinking 1/10^9 for any ontologically basic mental entities and 1/10^21 for a god.
Maybe the next time the survey should not allow probabilities exactly 0 or 1 (rather than saying they’ll be interpreted as 0+epsilon and 1-epsilon), and give the option to express probabilities as log-odds if they’re extreme. (Anyway, I didn’t give any probability lower than 0.1% or higher than 99.9% in my answer.)
In many cases, mine were a result of not wanting to type that many zeros. In the future, can we pick our units?
It’s hard to determine how likely it is I’m not high and staring at a bunch of skittles or something that I mistakenly think is a good argument, as Yvain has said.
I’m thinking 1/10^9 for any ontologically basic mental entities and 1/10^21 for a god.
Maybe the next time the survey should not allow probabilities exactly 0 or 1 (rather than saying they’ll be interpreted as 0+epsilon and 1-epsilon), and give the option to express probabilities as log-odds if they’re extreme. (Anyway, I didn’t give any probability lower than 0.1% or higher than 99.9% in my answer.)
… why not log odds all the time?