>. I know that
>you don't gain that much when it comes to truly random samples, but I
>don't think we ever dealt with how it would affect biased samples.
>Anyone with the statistical savvy to answer this one?
no such thing as truly random anyway--as in perfectly random--not when you're talking human beings. so, it's just like any other sample: you run tests to see how close to truly random you are against the probability that, by chance, you'll get certain kinds of results.
btw, we all know now *why* the N is so high right? if all of us who tried it took it twice because we wondered about the results.....
heh. no one had to even maliciously fudge the numbers by taking it multiple times! it could be that David M is high because people who score in his camp are skeptical or incompetent or both.:Þ
kelley