That is clearer to a wider audience, but at the expense of more words.
>It seems to me that your discussion must be limited to two experts who
>can agree on the context of the problem being addressed. An expert
>and a non-expert would not share the common background information
>that would make application to the discussion of additional evidence
>practical with Bayesian techniques.
My model applies to *any* situation where any two agents disagree
about some factual claim, as long as they understand what that claim
means. They do not need to share any understanding of other context.
>Are these computational limitations you speak of the situation where
>one party may not have the time or temperament to perform a complete
>or correct inductive analysis?
>Or, is one party simply unfamiliar with the formal analysis approach
>and unable to *formulate* the necessary computation?
The model applies to both of these cases.
>So, on the other hand, are you trying to show, vis a vis what Curt
>said, that normal "memetic replication" actually *does* end up
>equating to "a passable approximation of Bayesian inference"?
I cited a paper which indicated that evolutionary pressures reward
closer approximations to Bayesian reasoning, ignoring the
computational costs. In situations where those costs are small, then
a passable approximation is expected. When the costs are large, the
divergence should be larger. How much larger is hard to say.
>It's not that I (or the average person) want(s) to ignore expert
>opinions, it is simply that we can not make any use of them if they
>can not put into terms we can understand.
Consider debates on the effect of diet on lifespan, on the effect of
capital punishment on murder rates, the effect of military budgets on
deterring war, or on the age of the universe. Most everyone can
understand what these claims mean, even if they couldn't understand
most arguments about them. What debates do you have in mind?
>P.S. For those who might be interested, there is a descent overview
>called "A Short Exposition on Bayesian Inference and Probability" by
>John Stutz & Peter Cheeseman at
>http://ic-www.arc.nasa.gov/ic/projects/bayes-group/group/html/bayes-the
>orem-long.html
Btw, I used to work with John and Peter.
Robin D. Hanson hanson@hss.caltech.edu http://hss.caltech.edu/~hanson/