[net.physics] Bad Coin or Bad Luck?

crummer%AEROSPACE@sri-unix.UUCP (05/24/84)

From:            Charlie Crummer <crummer@AEROSPACE>

You're right about the coin test not being a proof.  In any sufficiently long
string of flips of a good coin there will be all imaginable sub-strings.  So
with a good coin there would be, e.g. a sub-string of 50 heads, one of 50 
tails, ... .  Since the probability of observing such a string is very low for
a good coin, however, if I observed such a string with a particular coin I 
would be willing to BET that the coin is biased.  No one expects a sure thing 
in gambling.

  --Charlie