Moderator: Ras
Code: Select all
Houdini 2.0c x64 +20 +131/-105/=224 52.83% 243.0/460
Rainbow UNLimited -20 +105/-131/=224 47.17% 217.0/460
Houdini will win this match, as expected. Here are my LOS values for these 460 games, and error bars for 95% confidence:geots wrote:Houdini 2.0c x64 vs Rainbow Unlimited
Next to last update- maybe Houdini didn't want any question marks. At any rate, the lead is widened.
Intel i5 w/4TCs
Fritz 13 gui
1CPU/64bit
128MB hash
Bases=NONE
Ponder_Learning=OFF
Perfect 12.32 book w/12-move limit
5'+5"
Match=500 games
[thru game 460]
Code: Select all
Houdini 2.0c x64 +20 +131/-105/=224 52.83% 243.0/460 Rainbow UNLimited -20 +105/-131/=224 47.17% 217.0/460
Nite/Morning-
george
Code: Select all
LOS_and_Elo_uncertainties_calculator, ® 2012.
----------------------------------------------------------------
Calculation of Elo uncertainties in a match between two engines:
----------------------------------------------------------------
(The input and output data is referred to the first engine).
Please write down non-negative integers.
Write down the number of wins (up to 1825361100):
105
Write down the number of loses (up to 1825361100):
131
Write down the number of draws (up to 2147483646):
224
Write down the confidence level (in percentage) between 65% and 99.9% (it will be rounded up to 0.01%):
95
Write down the clock rate of the CPU (in GHz), only for timing the elapsed time of the calculations:
3
---------------------------------------
Elo interval for 95.00 % confidence:
Elo rating difference: -19.66 Elo
Lower rating difference: -42.52 Elo
Upper rating difference: 3.03 Elo
Lower bound uncertainty: -22.86 Elo
Upper bound uncertainty: 22.69 Elo
Average error: +/- 22.78 Elo
K = (average error)*[sqrt(n)] = 488.50
Elo interval: ] -42.52, 3.03[
---------------------------------------
Number of games of the match: 460
Score: 47.17 %
Elo rating difference: -19.66 Elo
Draw ratio: 48.70 %
*********************************************************
Standard deviation: 3.2626 % of the points of the match.
*********************************************************
Error bars were calculated with two-sided tests; values are rounded up to 0.01 Elo, or 0.01 in the case of K.
-------------------------------------------------------------------
Calculation of likelihood of superiority (LOS) in a one-sided test:
-------------------------------------------------------------------
LOS (taking into account draws) is always calculated, if possible.
LOS (not taking into account draws) is only calculated if wins + loses < 16001.
LOS (average value) is calculated only when LOS (not taking into account draws) is calculated.
______________________________________________
LOS: 4.48 % (taking into account draws).
LOS: 4.55 % (not taking into account draws).
LOS: 4.51 % (average value).
______________________________________________
These values of LOS are rounded up to 0.01%
End of the calculations. Approximated elapsed time: 54 ms.
Thanks for using LOS_and_Elo_uncertainties_calculator. Press Enter to exit.
Ajedrecista wrote:Hello George:
Houdini will win this match, as expected. Here are my LOS values for these 460 games, and error bars for 95% confidence:geots wrote:Houdini 2.0c x64 vs Rainbow Unlimited
Next to last update- maybe Houdini didn't want any question marks. At any rate, the lead is widened.
Intel i5 w/4TCs
Fritz 13 gui
1CPU/64bit
128MB hash
Bases=NONE
Ponder_Learning=OFF
Perfect 12.32 book w/12-move limit
5'+5"
Match=500 games
[thru game 460]
Code: Select all
Houdini 2.0c x64 +20 +131/-105/=224 52.83% 243.0/460 Rainbow UNLimited -20 +105/-131/=224 47.17% 217.0/460
Nite/Morning-
george
More less -20 ± 23 Elo for 95% confidence; LOS values are around 4.5%, which means that Rainbow has ~ 1/22 of posibilities of being better. Houdini is still the king although Rainbow is playing a decent match... but Houdini 3 is expected to be released in September.Code: Select all
LOS_and_Elo_uncertainties_calculator, ® 2012. ---------------------------------------------------------------- Calculation of Elo uncertainties in a match between two engines: ---------------------------------------------------------------- (The input and output data is referred to the first engine). Please write down non-negative integers. Write down the number of wins (up to 1825361100): 105 Write down the number of loses (up to 1825361100): 131 Write down the number of draws (up to 2147483646): 224 Write down the confidence level (in percentage) between 65% and 99.9% (it will be rounded up to 0.01%): 95 Write down the clock rate of the CPU (in GHz), only for timing the elapsed time of the calculations: 3 --------------------------------------- Elo interval for 95.00 % confidence: Elo rating difference: -19.66 Elo Lower rating difference: -42.52 Elo Upper rating difference: 3.03 Elo Lower bound uncertainty: -22.86 Elo Upper bound uncertainty: 22.69 Elo Average error: +/- 22.78 Elo K = (average error)*[sqrt(n)] = 488.50 Elo interval: ] -42.52, 3.03[ --------------------------------------- Number of games of the match: 460 Score: 47.17 % Elo rating difference: -19.66 Elo Draw ratio: 48.70 % ********************************************************* Standard deviation: 3.2626 % of the points of the match. ********************************************************* Error bars were calculated with two-sided tests; values are rounded up to 0.01 Elo, or 0.01 in the case of K. ------------------------------------------------------------------- Calculation of likelihood of superiority (LOS) in a one-sided test: ------------------------------------------------------------------- LOS (taking into account draws) is always calculated, if possible. LOS (not taking into account draws) is only calculated if wins + loses < 16001. LOS (average value) is calculated only when LOS (not taking into account draws) is calculated. ______________________________________________ LOS: 4.48 % (taking into account draws). LOS: 4.55 % (not taking into account draws). LOS: 4.51 % (average value). ______________________________________________ These values of LOS are rounded up to 0.01% End of the calculations. Approximated elapsed time: 54 ms. Thanks for using LOS_and_Elo_uncertainties_calculator. Press Enter to exit.
Regards from Spain.
Ajedrecista.