[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums

Timothy

Posted By: Timothy Chow
Date: Friday, 29 June 2012, at 10:34 p.m.

In Response To: Timothy (Tom Keith)

What you say about the 100 coins is correct. But note that your conclusion is qualitative, not quantitative.

Let me try to put this in the plainest possible terms. It's blindingly obvious that Stick's numbers, as reported by Iancho, are much better than Mochy's numbers, or Falafel's numbers, etc. You don't need do crunch any statistics to see that. Some people suspect that Stick cheat, others insist that he doesn't, but all can see, plain as day, that his numbers are stratospheric.

So what do we gain by doing a fancy statistical test here? Nothing. Just as nothing would be gained by a fancy statistical test in your 100-coin case. If you somehow designed a test that yielded something other than the foregone conclusion, you'd know that your test was bogus or that you miscalculated something. Fancy tests are useful only when there's a subtle effect that might not be detected otherwise. And if you frame a question that is subtle enough to require a test, you're not going to get a reliable answer on retrospective data.

Messages In This Thread

 

Post Response
Your Name:
Your E-Mail Address:
Subject:
Message:

If necessary, enter your password below:

Password:
 

 

[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums is maintained by Stick with WebBBS 5.12.