Author: Paulo Soares
Date: 23:18:09 02/11/99
Go up one level in this thread
On February 11, 1999 at 15:41:25, Dann Corbit wrote: >Andreas Schwartmann asked an interesting question in r.g.c.c.: >"I wonder if anyone can enlighten me on how to use various test suites, like >LCT, LCT II and Covax. There are ceratin formulas on how to calculate the >playing strength according to these test suites, right?" > >Now, ignoring the fact that they are full of bugs and the measures are probably >bogus, how *does* one arrive at an ELO from a test suite evaluation? > >What is the actual mathematical basis for the calculations? The history shows that many scientific truths had been concluded through the experimentation. I compare the tests with that, We are still in the phase of the experimentation and far of reaching a definitive reply, a mathematical formula capable to find the relative force between programs, if this formula exists, inside of the mathematics for us known. On the other hand, exactly knowing that the tests are far to evaluate, with small margin of error, the relative force between the programs, I believe that the first thing that the majority of us makes when buying a new program, is to test it in a suite of any tests. I, for example, like the LCTII suite. I think that these tests also help to sell programs, and that is important for that they like computer chess. Summarizing, that more tests become, of preference with more knowledge, so that if it diminishes the margin of error, and so that let us can in them amuse more. Can the proposal of Bill McGaugh next to the reality? I think yes, and I go to test it!!! Best regards, Paulo Soares, from Brazil.
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.