Forum
Advisor Blog
Reviews
Strategies
Ideas
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
|
skrumgaer wrote
at 3:33 PM, Tuesday January 11, 2011 EST I don't have to accept Ryan's points as a definition of skill. At one time we had the elo system, where skill was not defined by the level of table you played at but by the place performance level of the player you placed better than. Also, in tournaments, the "money" points are determined by place of finish; there is no dom in the tourneys. Ryan's point systems are changable. Which one is the measure of "true" skill?
|
|
|
skrumgaer wrote
at 3:36 PM, Tuesday January 11, 2011 EST Incidentally, my other stat, the baseball-style standings, does have negative deviation for fifths, sixths, and sevenths.
|
|
montecarlo wrote
at 3:47 PM, Tuesday January 11, 2011 EST my issue is that the TAZD basically says 1st=2nd=3rd=4th=5th=6th=7th. two people have the same distribution: the zero datum. except person one has 5% more 1sts and 5% less 7ths. person 2 has 5% less 1sts and 5% more 7ths. according to TAZD, they have equal skills. i just dont understand how its logical to conclude that these people have the same skill. please justify why the TAZD is correct to call these players equally *skillful. (*not equally deviating).
lets use your ELO example. given these two players, the first player will 99.99% of the time have a higher ELO, higher ranking. lets use the current points system. 99.99% of the time, the first player will have more points. lets use common sense: 99.99% of the time, the first player is more skillful. lets use a poll of people who are still reading this thread: 75% of the people think that the first player is more skillful (Vermont, chloe, monte), whereas 25% refuse to take sides (skrum). how about TAZD? it says the players are equally skillful. ludicrous. its a nice statistic, but it would be much more useful if you were to tweak it. otherwise, its simply a deviation metric which cannot decipher between good deviation and bad deviation. monkeys are better than every single player that has ever played the game of kdice. how should this EVER be true of a reasonable statistic? |
|
|
montecarlo wrote
at 3:52 PM, Tuesday January 11, 2011 EST and its not like an improved TAZD would dramatically change your rankings. i would hazard a guess that no one would move up or down more than 10 spots, and that the top 3 would remain the same order. the tweak would just make the stat more correct, and would close loopholes that TAZD currently leaves open. why not go through the minimal effort to make your statistic more correct.
i find it amazing how much effort you have gone through defending the TAZD in its current form (youve read at least 150 posts, and written at least 20 yourself, which equates to a LOT of time). with the same time, you couldve added the one extra column to your spreadsheet that would make your TAZD stat foolproof (monkeyproof, even). |
|
|
skrumgaer wrote
at 5:18 PM, Tuesday January 11, 2011 EST Different deviations by definition imply different skills. Consider mutations. Mutations are differences. We consider some mutations "favorable" because they enhance the ability to survive in a particular environment. Sickle-cell anemia is an unfavorable mutation, except that it confers immunity to the particular illness spread by tsetse flies. In that environment it would be a favorable mutation. So it's the environment that determines what is a good or bad mutation.
Likewise with skills. The zero datum is our best indicator of the lack of particular skills that perform well in the kdice environment. That environment is shaped by people who enjoy playing kdice and have invested in the game. That environment does not include people that want to flag out for the sake of flagging out. Just as adults play contract bridge and poker, not slapjack. Statistical indicators in general are not free of error. The standard linear regression is called the "best" linear unbiased indicator (BLUE). But it is not a perfect indicator. I am not making a claim that the TAZD is a perfect indicator. It is merely the best indicator for the kinds of players who have made an investment in kdice. |
|
Vermont wrote
at 12:46 AM, Wednesday January 12, 2011 EST Does skrum really think that he can call tazd a measure of skill, when he at the same time says he can ignore Ryan's (or the kdice community's) general defintion of skill?
I'd be curious to hear how he defines skill. Since the tazd is supposedly a measure of skill, according to him, that must mean something. If his measure of skill is just how much a player deviates from the norm, then so be it. That's what everyone (except him of course) has been saying the tazd is for some time. I think people fundamentally agree that finishing higher is generally better, and finishing higher more often indicates a better player than someone who finishes lower. How anyone can disagree with such a basic concept is just beyond me. As monte said, 1st > 2nd > 3rd > 4th > 5th > 6th > 7th. Why is this so hard to understand? |
|
superxchloe wrote
at 1:36 AM, Wednesday January 12, 2011 EST "Different deviations by definition imply different skills."
Do we all agree that 'skill' in this instance is 'being good at kdice'? If not, then this argument is unwinnable. Let's say that earning 100% 7th places would make me extremely skillful, but skillful at not playing kdice rather than being good at kdice. This would earn me a kickass TAZD. The TAZD is, according to "the collected works of skrumgaer," supposed to be a measure of positive skill (ie, being good at kdice). I should not be rewarded in a statistic meant to measure positive skill for kdice when I am extremely skillful at something else entirely. The most frustrating part of this discussion has not been the disagreements. It has been your unwillingness to listen, skrum. I understand that you believe in the TAZD as the best measure of skill that currently exists, but you admit that it is not perfect. I really think that if someone suggests a change, you listen to what they have to say and their argument for the change. imho, it is ridiculous that you have spent so much time twisting your arguments but haven't even referenced the suggested changes. |
|
|
skrumgaer wrote
at 6:31 AM, Wednesday January 12, 2011 EST Chloe:
You might want to take a look at Entry #11 in this blog: "KDice Taxonomic Study Sample #1: Meet your Closest Relatives" by me. It is a dendrogram that shows relationships between different percentage profiles of players, which I have characterized with names like "sphinx", "hyena", "horse", etc. These are different styles, or skills, in playing kdice. To compare how different ways of measuring skill are measuring the same thing is to use a test such as the Spearman rank-correlation test. Take the top 100 by Ryan points and compare the ranking by that measure with another, such as the tazd, baseball-style standings, asr, etc. You will get a quantity called r, which can range from +1 (perfect correlation) to -1 (perfect anticorrelation). Skills can also be found by using factor analysis. It has been used to analyze decathletes. Does the decathlon measure ten different distinct skills? |
|
|
Vermont wrote
at 9:12 AM, Wednesday January 12, 2011 EST Somehow I'm not surprised that skrum completely ignored my post.
However, I'll respond to yours. The decathlon measures ten different sports. Look up the root of the word if you need more to help you understand that. Kdice is a single game. You are once again comparing different styles/results of playing one game to the results from completely different games/events. Texas hold em, for example, has many different styles of play - however, it is easily understood that a better player will finish higher more often, and that people with their styles are still playing the same game. The (more) equivalent analogy would be if Ryan had a score that combined scores from kdice, xsketch, and gpokr. |
|
|
Vermont wrote
at 9:14 AM, Wednesday January 12, 2011 EST And I'm sure factor analysis for decathletes does not reward them in the rankings for coming in last more often than other decathletes. That would, for very obvious reasons, be terribly stupid.
|
