Author: Peter Fendrich
Date: 06:31:57 03/08/02
Go up one level in this thread
On March 08, 2002 at 08:07:24, Mike Hood wrote: >As has already been discussed in other threads, ELO ratings only give the >relative rankings of competitors in a limited pool, although by extending the >pool to encompass the whole world the ratings can be considered absolute. > >The SSDF rating lists can only be taken seriuously if the pool of computer >programs is periodically calibrated by taking into account games between >computers and humans. > >To what extent is this done? > >Are only games between grandmasters and top programs considered? Or also >verifiable tournament condition games between club players and computer >programs? 1) There are no absolute ratings. It's always the difference between ratings within the same pool that the ELO system calculates. Even human ratings consists of national pools. They even have differences in how to compute the ratings and they also differ from the FIDE ratings. The best you can do is to calibrate the different pools with each other to get somewhat equal levels but in no way interchangeable ratings. 2) The SSDF ratings are computer games only. Playing computers are not the same as playing humans. We can calibrate this rating pool as much as we wan't with human rating pools but will never get interchangeable ratings. The differences within the SSDF list are not comparable with how the differences would be if the list also included humans. Saying all this I would also like to add that the SSDF list is the most accurate rating list (compared to the human ones) there is, saying it is as a pure computer games list. Regards, Peter
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.