Author: Mogens Larsen
Date: 00:44:01 07/29/00
Go up one level in this thread
On July 28, 2000 at 18:25:45, Ratko V Tomic wrote: >Well they're both scale models of a phenomenon, i.e. they're not identical with >the phenomenon, so they won't reproduce/mimick the phenomenon exactly. The >question is which model, human evaluation or the rating computation on a small >sample of games has _greater_ predictive power regarding the future games. Or if >you had to bet which one will come closer, would you pick the human judgment or >the rating prediction based on a handful of games? Probably the human evaluation, but it's an artificial question. You don't do predictions on a handful of games using statistics for obvious reasons. >Yes, but there are patterns to the variability and human is surely better in >picking out such patterns than a simple memoryless source statistical model (the >base for coin flipping and rating computation). No, there are not necessarily recognisable patterns and it's not possible to evaluate their stability using a handful of games. >They're much less random within the human model. No, again. It's like choosing between very, very random and very random. No matter the choice, the actual estimation is uncertain and useless. Unless you care very little about the usability of the information. A strong player can make general observations about strengths and weaknesses in general terms in reviews. Notice however, that when they want to explain how strong it really is, the reviewer inform you on his/hers ability to beat it at chess. That is win/loss ration and pure empirical data without too many faulty impressions. Noone serious uses impressions alone if not backed by convincing empirical data. That's a fact, whether you like it or not. Best wishes... Mogens
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.