> This [idea that a historical explanation will always fall into the

> world of POSSIBILITIES, and occasionally PROBABILITIES] is a cop-

> out ... Mere PLAUSIBILITY is not sufficient. We need to strive for

> ways of evaluating the relative credibility of competing

> hypotheses. (emphasis mine-MWG)

I wonder if, in terms of probability, everyone understands these

words in the same way, namely:

'possible' = probability > 0 (hence of no interest)

'probable'/'likely' = probability > 50% (of great interest)

'plausible'/'credible' = probability "significant", but < 50%

No mathematical value can be assigned to the latter category, tho

intuitively it would seem to have to be at least 10-33%. It may in

fact be only a measure of how closely a suggestion accords with

one's intuitions.

David Hindley writes:

> ... we do not have knowledge of the universe population from which

> the samples were drawn. That means we are not really working in

> the world of probabilities, but only possibilities!

I think this is a misunderstanding of "the world of probabilities".

I'd say that real-world probabilities (as opposed to artificially-

controlled test situations) are always assessed within a context of

incomplete knowledge. It's understood that the degree of probability

is relative to what we know. One of the things that enters into the

calculation is an assessment of the likelihood that further samples

would significantly differ from what is known. It's always POSSIBLE

(> 0%) that further evidence will radically alter the picture, since

the evidence available from the real world is never scientifically

selected, but that's what makes "the world of probabilities" what it

is.

Mike Grondin

Mt. Clemens, MI