| |
BGonline.org Forums
Bob Koca, ask not for whom the bell tolls
Posted By: Casper van der Tak In Response To: Bob Koca, ask not for whom the bell tolls (Matt Cohn-Geier)
Date: Saturday, 30 June 2012, at 8:02 a.m.
The problem is in the 'one could' part. First, one could, but does one? Second, how do you do it if you don't know from how many coin-flippers the test subject is chosen, and the only thing known is having the best coin-flip result?
The problem remains, if the hypothesis for a statistical test is formed on the basis of the data, the usual test statistics change their interpretation.
| |
BGonline.org Forums is maintained by Stick with WebBBS 5.12.