I did. Source or reasonable example?
The OP just said the formula was not meant for the 700 rating, which he claims was not found in his research. (There exists in fact many such rated players).
What good is the formula, what validity does it hold if it does not apply to any rating? Absolutely none.
What good is the formula, what validity does it hold if it does not apply to any rating? Absolutely none.
Is this all ya got?
"give me your sources" !
Too funny
"give me your sources" !
Too funny
"There exists in fact many players [rated below 700]"
Your statement is false. Proof: lichess.org/stat/rating/distribution/classical
"What good is the formula, what validity does it hold if it does not apply to any rating? Absolutely none."
What good is Aspirin if it can't cure headaches in Martians? Absolutely none!
What good is the contraceptive pill if it doesn't prevent pregnancy when the man takes it? Absolutely none!
As I demonstrated empirically, in the graph posted above, the formula produces reasonable predictions for existing Lichess profiles (which is the range that should interest us).
Your statement is false. Proof: lichess.org/stat/rating/distribution/classical
"What good is the formula, what validity does it hold if it does not apply to any rating? Absolutely none."
What good is Aspirin if it can't cure headaches in Martians? Absolutely none!
What good is the contraceptive pill if it doesn't prevent pregnancy when the man takes it? Absolutely none!
As I demonstrated empirically, in the graph posted above, the formula produces reasonable predictions for existing Lichess profiles (which is the range that should interest us).
Nice work dudeski!
From a statistics standpoint it is very reasonable and fits well with expected results. It is much better than a simple number to be subtracted from Lichess rating.
I also think that you have conscienciously and thoroughly adressed the limitations (most of them inherent to statistics and others inherent to data collection) plus the delimitation (to make an estimate).
I am very impressed that there is enough interest to fill 24 pages and more coming. Some of it is beginning to be reruns though, but that can't be helped.
Cheers
From a statistics standpoint it is very reasonable and fits well with expected results. It is much better than a simple number to be subtracted from Lichess rating.
I also think that you have conscienciously and thoroughly adressed the limitations (most of them inherent to statistics and others inherent to data collection) plus the delimitation (to make an estimate).
I am very impressed that there is enough interest to fill 24 pages and more coming. Some of it is beginning to be reruns though, but that can't be helped.
Cheers
Thanks for your comment @prettselk
But to be fair, I think you're being too generous. There really hasn't been that much interest. Most of those 24 pages are just me and that other guy talking past each other :)
But to be fair, I think you're being too generous. There really hasn't been that much interest. Most of those 24 pages are just me and that other guy talking past each other :)
@mdinnerspace:
Many thanks for livening up this thread again. What would we do without your aggressive tone and destructive demeanor? We might even forget we discuss in an internet forum!
> The OP has yet to address the issue
> regarding his "formula".
There is no "issue". It was offered as a "best effort" from the beginning and - while it is interesting to discuss to maybe find ways to make the prediction better - he, me and nobody else for that matter is obligated to anything. If you don't like it, don't use it.
> A given formula of...
> x and y (averaged) + z (any number used as a constant) = D
> is invalid.
Tell that to the (ancient) mathematicians who found out that the general linear function is of the form
y = mx + c
where m is the slope and c is - a constant!
> People shouting... give me your sources!
Yes - and why not? Whatever one says sources (as well as other reasoning) add to the credibility of what is said. This is a common trait of serious discussions and if you refuse to offer either sources (=reasoning of others) or your own reasoning you show that you are not interested in such a serious discussion.
I am really fed up, go away, kiddie. Here are grown-ups talking.
krasnaya
Many thanks for livening up this thread again. What would we do without your aggressive tone and destructive demeanor? We might even forget we discuss in an internet forum!
> The OP has yet to address the issue
> regarding his "formula".
There is no "issue". It was offered as a "best effort" from the beginning and - while it is interesting to discuss to maybe find ways to make the prediction better - he, me and nobody else for that matter is obligated to anything. If you don't like it, don't use it.
> A given formula of...
> x and y (averaged) + z (any number used as a constant) = D
> is invalid.
Tell that to the (ancient) mathematicians who found out that the general linear function is of the form
y = mx + c
where m is the slope and c is - a constant!
> People shouting... give me your sources!
Yes - and why not? Whatever one says sources (as well as other reasoning) add to the credibility of what is said. This is a common trait of serious discussions and if you refuse to offer either sources (=reasoning of others) or your own reasoning you show that you are not interested in such a serious discussion.
I am really fed up, go away, kiddie. Here are grown-ups talking.
krasnaya
Ha ha, well, on behalf of science and humanity: thanks for trying to explain.
Also: in many ways interest is interest.
Having gotten lost in the methods for a time (I am a biologist that likes statistics) I will now try to calculate my approximate FIDE Elo from my Lichess rating.
If it turns out lower than I want, I might be back for some angry trolling :D
Also: in many ways interest is interest.
Having gotten lost in the methods for a time (I am a biologist that likes statistics) I will now try to calculate my approximate FIDE Elo from my Lichess rating.
If it turns out lower than I want, I might be back for some angry trolling :D
hehe
The OP insists on looking at his graphs for proof.
I observe no such evidence that players with an online rating below 1800 will have a higher OTB FIDE rating and players above 1800 will have a lower OTB Fide rating.
The given "formula" is unsound. Basic mathematical principles tells us the added constant of+187 is not applicable.
I observe no such evidence that players with an online rating below 1800 will have a higher OTB FIDE rating and players above 1800 will have a lower OTB Fide rating.
The given "formula" is unsound. Basic mathematical principles tells us the added constant of+187 is not applicable.
This topic has been archived and can no longer be replied to.