Author: Uri Blass
Date: 02:31:13 08/22/03
Go up one level in this thread
On August 22, 2003 at 04:53:11, Gian-Carlo Pascutto wrote: >On August 22, 2003 at 04:43:52, Uri Blass wrote: > >>Maybe there is a misunderstanding. >>I did not mean to say that it is statistically significant when I said >>evidence. > >There's a difference between an indication and evidence. Ok I will use the word indication later. I thought that the meaning of evidence is different. There are cases when a person is considered to be not quilty of a crime because the evidence against him is not enough(I hope that I do not do wrong translation from hebrew to english). I know that statistics is not used for these decisions but free generalization of the meaning of evidence led me to believe that it means indication that program A is better than B. > >>The point is that even if the data is not statistically significant it suggests >>something > >That is true. > >>and I do not think that it is right to ignore the data only because >>of the fact that it is not statistically significant. > >I think it is. (I don't use a hard threshold obviously, but I do >need a strong indication it wasn't just luck.) > >>I know that there are programmers who do not do it >>see >>http://www.f11.parsimony.net/forum16635/messages/52921.htm >>for comparison that he used to decide that the change is not productive >>see >>http://www.innconx.com/~wildcat/279.html >>http://www.innconx.com/~wildcat/282.html >> >>282 scored one point more than 279 but the programmer decided not to accept the >>change. > >If I look at that, I conclude that it's either not making a difference >or the difference is too small to worry about. The point is that if I have to choose which version to use in a tournament I tend to choose 282 and not 279. I agree that the difference is very small and may be even to the opposite direction than the direction that I guess. > >>Of course the difference is too small to get significant results but there is a >>basis to give bigger probability to the event that 282 is better and not to the >>event that 279 is better. > >It's way to small to make a decision on. I see no reason not to make a decision to use 282 Using 279 is also a decision and using 282 seems to me slightly better decision. Uri
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.