Forum
Fatman_x takes the 2010 TAZD; computation of complete standings in progress.
Posted By: skrumgaer at 6:51 PM, Saturday January 1, 2011 EST
Here are Fatman_x's final stats:
1631 22% 16% 13% 12% 10% 11% 11% 22535 Fatman_x
Olkainry38 did not play any additional games after Dec 21.
Here were the two leaders on Dec 21:
1591 22% 16% 13% 13% 10% 11% 11% 21975 Fatman_x
0894 22% 20% 16% 13% 11% 08% 07% 21798 olkainry38
The November scores are below. They were recomputed when I found I had been using the 2009 datum instead of the 2010 datum.
The Test Against Zero Datum (TAZD) is a weighted sum of the squares of the differences between a player's percentage profile and the profile of a typical player with a zero score, adjusted according to the square root of the number of games played. If you would like to enter the cumulative TAZD competition for 2010, reply to this thread in the account that you want to enter.
In 2010, the cumulative TAZD began in April, because some January, February, and March profiles had corrupted percentages.
A minimum of sixty regular games per month was required.
Entries show number of games, percentages, and player name.
A minimum of 540 regular games played was required to remain in the standings as of December 31.
Here are the end of November standings with the new datum.
0815 22% 20% 16% 13% 11% 09% 07% 20192 olkainry38
1324 22% 16% 13% 13% 10% 13% 11% 19645 Fatman_x
0886 21% 18% 18% 13% 11% 08% 07% 19382 the full monte
1612 15% 19% 16% 14% 14% 11% 07% 17412 Xar
2297 18% 15% 14% 15% 13% 13% 10% 17190 Fonias
1282 19% 15% 14% 14% 13% 13% 09% 14698 ProxyCheater
1089 19% 16% 12% 15% 13% 12% 09% 14359 ZIGIBOOM
1817 16% 18% 12% 10% 11% 13% 16% 14038 cool g
0731 18% 22% 12% 10% 08% 11% 16% 14010 leeroy jenkins
1810 19% 14% 12% 12% 13% 15% 12% 13270 caesar-blue
2990 13% 11% 11% 08% 09% 10% 34% 12928 noamlang1
0519 21% 15% 18% 11% 12% 08% 12% 12080 chaiNblade
1597 19% 14% 09% 09% 10% 13% 24% 11916 greekboi
0769 22% 14% 09% 13% 13% 13% 14% 11355 dasfury
1054 18% 14% 13% 13% 12% 11% 15% 09627 yellowfin
0698 17% 15% 10% 13% 14% 14% 13% 06707 speciale528
0662 17% 14% 12% 12% 13% 13% 15% 06340 AlexBallDrop
1122 11% 15% 15% 14% 11% 12% 18% 05785 pooch723
1625 16% 12% 11% 10% 12% 15% 22% 06512 kendawg
0613 14% 11% 17% 11% 11% 15% 16% 04945 vIRGI
1631 22% 16% 13% 12% 10% 11% 11% 22535 Fatman_x
Olkainry38 did not play any additional games after Dec 21.
Here were the two leaders on Dec 21:
1591 22% 16% 13% 13% 10% 11% 11% 21975 Fatman_x
0894 22% 20% 16% 13% 11% 08% 07% 21798 olkainry38
The November scores are below. They were recomputed when I found I had been using the 2009 datum instead of the 2010 datum.
The Test Against Zero Datum (TAZD) is a weighted sum of the squares of the differences between a player's percentage profile and the profile of a typical player with a zero score, adjusted according to the square root of the number of games played. If you would like to enter the cumulative TAZD competition for 2010, reply to this thread in the account that you want to enter.
In 2010, the cumulative TAZD began in April, because some January, February, and March profiles had corrupted percentages.
A minimum of sixty regular games per month was required.
Entries show number of games, percentages, and player name.
A minimum of 540 regular games played was required to remain in the standings as of December 31.
Here are the end of November standings with the new datum.
0815 22% 20% 16% 13% 11% 09% 07% 20192 olkainry38
1324 22% 16% 13% 13% 10% 13% 11% 19645 Fatman_x
0886 21% 18% 18% 13% 11% 08% 07% 19382 the full monte
1612 15% 19% 16% 14% 14% 11% 07% 17412 Xar
2297 18% 15% 14% 15% 13% 13% 10% 17190 Fonias
1282 19% 15% 14% 14% 13% 13% 09% 14698 ProxyCheater
1089 19% 16% 12% 15% 13% 12% 09% 14359 ZIGIBOOM
1817 16% 18% 12% 10% 11% 13% 16% 14038 cool g
0731 18% 22% 12% 10% 08% 11% 16% 14010 leeroy jenkins
1810 19% 14% 12% 12% 13% 15% 12% 13270 caesar-blue
2990 13% 11% 11% 08% 09% 10% 34% 12928 noamlang1
0519 21% 15% 18% 11% 12% 08% 12% 12080 chaiNblade
1597 19% 14% 09% 09% 10% 13% 24% 11916 greekboi
0769 22% 14% 09% 13% 13% 13% 14% 11355 dasfury
1054 18% 14% 13% 13% 12% 11% 15% 09627 yellowfin
0698 17% 15% 10% 13% 14% 14% 13% 06707 speciale528
0662 17% 14% 12% 12% 13% 13% 15% 06340 AlexBallDrop
1122 11% 15% 15% 14% 11% 12% 18% 05785 pooch723
1625 16% 12% 11% 10% 12% 15% 22% 06512 kendawg
0613 14% 11% 17% 11% 11% 15% 16% 04945 vIRGI
superxchloe wrote
at 5:46 PM, Wednesday January 12, 2011 EST As a chi-square test, the TAZD is a measure of deviation from a set of expected values. It makes a good attempt at measuring positive skill. Among the top 100 or yearly competitors, I would expect that r would be approximately .5 +/- .1, indicating a weak positive correlation. Because the monthly TAZD samples the best players, there is some selection against players who would do well in the TAZD but poorly in the ASR (like the monkey). I would accept the TAZD as a measure of positive skill if r is greater than one-half.
If you use the data from the Yearly ASR and the 2010 TAZD, r=.43 which is within the range I expected. Throw in the monkey with the average number of games and ppg (Skrum's untrained monkey, not Monte's slightly smarter monkey), and r=.27. There is a weak correlation between the ASR and the TAZD. As I have said before, the TAZD makes a good attempt at measuring positive skill. However, it could be better. Making the TAZD better would be a simple tweak. The tweak drops the monkey into dead last for the TAZD, and r increases to .55. Since you have so many statistics and you can't make sortable lists, posting all the stats in one post is slightly problematic, unless you want to post several long lists rather than each of the players' stats next to their name. If it were me, I would list the winners of each stat for the month, then post a list sorted by one of the stats, and a published google doc so anyone who wants to can download the info and sort by whichever stat they want to examine further. The other benefit of posting all the stats in the same post is that you don't flood the forum with several posts, pushing active posts farther back in pages. |
skrumgaer wrote
at 9:06 PM, Wednesday January 12, 2011 EST Thanks, chloe.
Since I am still snowed in, could you run a monthly TAZD against a monthly ASR? And each against the month's top 100 as ranked by the leaderboard? As for doing more than one stat in the same post, if there is not too much changing of ranks between the stats, I could do two at a time without straining the reader. Like when I did the TAPL with the TAZD. One column with the one stat, one with the other stat, and player name. |
superxchloe wrote
at 10:19 PM, Wednesday January 12, 2011 EST Being snowed in is a reason to run stats, not a reason to NOT run stats :)
r values for December 2010: ASR vs Rank: 0.454864232 ASR vs TAZD: 0.755573832 TAZD vs Rank: 0.157100141 TAZD* vs Rank: 0.147039509 TAZD* vs ASR: 0.754502738 I did not do a TAZD* vs TAZD because they are extremely similar. Also interesting: ASR multiplier vs TAZD: 0.779788204 ASR multiplier vs Rank: 0.139490848 |
montecarlo wrote
at 11:29 PM, Wednesday January 12, 2011 EST when you run the tests versus RANK, is it rank minus extraneous points, or does it include tourneys etc?
|
superxchloe wrote
at 12:35 AM, Thursday January 13, 2011 EST oh good point monte. I'll run the rankings again sans ersatz points in the morning.
|
superxchloe wrote
at 11:12 AM, Thursday January 13, 2011 EST Games*PPG vs ASR: 0.976129908
Games*PPG vs TAZD: 0.675675331 Games*PPG vs TAZD*: 0.671824494 Games*PPG vs ASRm: 0.512295265 While I did not correct this for ties (and thus the stats aren't completely accurate), they're close to what it would have been if I had corrected. This basically says to me that the ASR relies heavily on table points (which we already knew), and a thought that I have had for some time is that perhaps this should not be the case. Thoughts? As you can see, TAZD and TAZD* have extremely similar r values. This is because TAZD* only changes the scores of about 8 people in the top 100, and only bump them up or down one place (usually). In the 2010 TAZD, noamlang1 ended up ranked 15th, based on my data set. When I ran the TAZD* instead, he dropped to 20th. When I looked at raw scores, pre-game weighting, he was dead last, as I believe it should be. |
skrumgaer wrote
at 12:45 PM, Thursday January 13, 2011 EST noamlang1 has explicitly said that at zero level tables, 5th=6th=7th. If negative raw scores were to count, noam would not have taken this strategy and his behavior would have been different.
|
montecarlo wrote
at 2:41 PM, Thursday January 13, 2011 EST i dont disagree with noams strategy. i usually employ it myself. however, that might mean my overall 7th place percentage bumps up 0.2% or so. if it takes you a hundred games to get off the 0 tables, you dont have much skill.
the strat of instaflagging on 0 tables because 4th=7th should NOT cause a significant deviation from the norm if the player is skillful at acquiring points on regular tables. |
montecarlo wrote
at 2:49 PM, Thursday January 13, 2011 EST as far as methods to rank ersatz points, i dont think there is any way to separate tourney points from other ersatz points right? if so, it would be interesting to calculate for each player what percentage of max points he/she took away from each tourney, on average.
if you win every tourney you enter, you get a score of 1.000. if you never get a payout, you get a score of 0.000. i understand it's impossible to see past the last 10 tourney results on any player page... but with kakk's programming, he could just check for additional tourney results every 2 days, and add them into the average. the only issue that might happen is that members might have significantly higher results than nonmembers, but im not quite sure if that will happen. interested to see, though. thoughts? |
skrumgaer wrote
at 3:02 PM, Thursday January 13, 2011 EST There are lots of tourney stats on the tourney tab, but not arranged by player. But if you want to lump all players together you might get some interesting results.
|