Author: Sune Fischer
Date: 09:30:53 06/03/02
Go up one level in this thread
On June 03, 2002 at 12:10:33, Chris Carson wrote: >>Do you assume that the mean rating should stay constant? > >No, I only said that you can compare the mean ratings, I did not say it stayed >the same. I'm not sure what you mean by "you can compare the mean rating". Mathematicly this is trivial, but what conclusions can you draw from it? >> >>Today we have the internet, which means any chess player can get a mental >>workout 8 hours a day if he wants to. >>Today we have very strong programs that can assist our analysis and speed up our >>individual improvements. >>Today chess theory has evolved, openings refuted, novelties found... >> >>You can't say for sure that the rating should remain constant, if you enforce >>this on the pool then a 2500 player back then may not be as strong as a 2500 >>player today how knows all the latest and hottest variants. > >I never said it remained constant. All I have said is that it is valid to do a >comparison and hypothesis testing to see if ratings inflation exists. It may. >Hypothesis testing will also confirm or deny the significance of any change. It >may or may not be significant, that is what hypothesis testing determines. yes, if you could do a hypothesis testing, of course, but how do you do that? I hypothesise there has been a slight inflation in rating, but also a slight increase in average strength of top playes. This means we should subtract a bit from the current ratings of players, but their mean should still be higher. How do you design a test to confirm this hypothesis? You can't very well ask the players from the past to solve a given testset of positions... You need some *fixpoint*, some universial scale to match up against, so far we have been unable to design such an scale. >> >>I think objectively it is "easier" today to reach the level of a 1970's GM, >>because of all the aids available to the player. This doesn't "prove" or >>disprove inflation of rating, we just cannot compare strength across the time >>barrier. >> >>-S. > >We can compare strength across time and we can do studies to determine the >effects of factors you listed above (they may have no effect or they may have a >significant effect). We could also set up a study to determine if it is >"easier" today. It may be, but I would need to see research on that before I >would make that claim. Same for ratings inflation. Please tell me how to compare strengths when the elo scale is useless? Why don't we switch to that method and throw out the elo system then? -S.
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.