On Sat, Apr 26, 2008 at 8:52 PM, Steve Richfield <[EMAIL PROTECTED]> wrote: > > On 4/24/08, Vladimir Nesov <[EMAIL PROTECTED]> wrote: > > > A theory is strong not when data support it, or when it doesn't > > support the wrong data, but when it can distinguish between the two. > > God hypothesis is as useful as a coin flip in its power to detect the > > facts. A weak theory, on the other hand, that says "zebra!" only in > > 0.09% of cases when the track is zebra's, and in 0.08% of cases when > > it's not zebra's, is much better. > > > Hmm, if I remember my math from long ago... > To distinguish between these two rates would take ~10^8 observations - > probably more than anyone would get in a lifetime. Until then, you would go > with the best explanation that is available, namely, that an unseen power > (maybe God, or maybe just superstition in the mind of the zebras) is > controlling this. In any case, the travels of zebras is almost certainly NOT > random.
Yes, the Ways of Zebras do not transcend our ability to comprehend. But what are those 10^8 observations supposed to distinguish between? You can be quite certain in ability of this test without observing any zebras. You just need indirect evidence. For example, such a test can be obtained from a much better test that is right almost 100% by adding just right amount of noise. This is however not the point... -- Vladimir Nesov [EMAIL PROTECTED] ------------------------------------------- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244&id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com
