|
On September 20 2010 06:25 DonKey_ wrote:
...um does it not bother anyone that terrans wins are only so high cause morrow has won a grand total of 12! tournaments... this might be more conclusive if it was more evenly spread between the terran players. You're assuming Morrow's wins would go to non-Terrans.
Dealing them out proportionally to the Morrow-absent results gives 3 more to Toss and 1 more to Zerg.
So 48 T, 25 P, 5 Z.
Yeah, it really bothers me that Morrow is included. Things would be so different otherwise. :/
|
just wait for patch 1.1.2, it will fix everything! 
|
I'm sure this has been mentioned, so I apologize if it has.
It should be noted and always thought about that this is one (incomplete) data set. On its own, this yields no real conclusions or even correlations. To make any assumptions you would need other data sets including but not limited to: (a) distribution of races entered into said tournements (b) a metric for judging skill to further polish the numbers (there's no point in including non top players) and (c) some manner of standard deviation or statistical probability -- which is very difficult. Drawing any conclusions from this set of data alone is just as foolish as using Battle.net rankings as a metric of balance.
|
ok gospel you can take zerg and I'll take toss and terran for upcoming tournaments and I'll give you 5:1 odds
|
Guitarizt: Gospel was stating mathematical fact. It is not his opinion. The interpretations can be objective, but he states the ground facts to FORM opinions based on. Get educated or don't comment on posts like that.
|
On September 29 2010 13:38 NameOfTheLawl wrote:
Guitarizt: Gospel was stating mathematical fact. It is not his opinion. The interpretations can be objective, but he states the ground facts to FORM opinions based on. Get educated or don't comment on posts like that.
agreed. If you're arguing with some using math and logic, use math and logic to counter his arguments.
|
The information gospel listed leads directly to making conclusions about race balance based on the OP's info. Guitarizt was simply saying that regardless of balance, you could draw a tournament winner out of a hat and odd are less than expected that it would be zerg. I think his only assumption was that these trends would continue as is. I'm not going to try to say whether patch 1.1 was enough to break his assumption.
|
lol is the OP being updated?
cos there's like 6 more terran victories to be added :D
|
I swear, people who come in here talking about how you need all this additional information such as sample size and correlation etc etc to prove what these results imply. You guys are like lawyers. Arguing about something that is clearly wrong under retarded technicalities. What happened to common sense. You don't need a physics degree to know that coffee coming out the pot is hot. But you accountant and statics majors try to distort the blatant evidence that zerg is under-powered by saying you need more data. gtfo. Either zerg doesn't win tournaments because they're UP or no one plays zerg because they're UP. What are you arguing?
|
On September 29 2010 15:08 Count_Waltz wrote:
I swear, people who come in here talking about how you need all this additional information such as sample size and correlation etc etc to prove what these results imply. You guys are like lawyers. Arguing about something that is clearly wrong under retarded technicalities. What happened to common sense. You don't need a physics degree to know that coffee coming out the pot is hot. But you accountant and statics majors try to distort the blatant evidence that zerg is under-powered by saying you need more data. gtfo. Either zerg doesn't win tournaments because they're UP or no one plays zerg because they're UP. What are you arguing?
I am questioning your post since that's not what ppl are arguing. People are not arguing 'Z is not UP' but saying that the 'OP's data' is not support this and people should not conclude 'Z is UP' by looking at OP.
Let's look at it this way, if you take Morrow (who had won A LOT) out of the equation, the Terran win goes down significantly to the point Terran has less win than Protoss or even Zerg. That itself should tell you that the data provided does not say anything about the current balance. I am sure there are other data (though quite small) that could say 'Z is UP' but the OP's data does not say anything and that's what rational people on this topic are arguing about. An irrational person would be arguing NO THIS SUPPORTS the data 'Z is UP' look at those numberz. People aren't lawyers but people will argue if someone calls an orange, an apple.
|
On September 29 2010 15:18 ooni wrote:Show nested quote +On September 29 2010 15:08 Count_Waltz wrote:
I swear, people who come in here talking about how you need all this additional information such as sample size and correlation etc etc to prove what these results imply. You guys are like lawyers. Arguing about something that is clearly wrong under retarded technicalities. What happened to common sense. You don't need a physics degree to know that coffee coming out the pot is hot. But you accountant and statics majors try to distort the blatant evidence that zerg is under-powered by saying you need more data. gtfo. Either zerg doesn't win tournaments because they're UP or no one plays zerg because they're UP. What are you arguing? I am questioning your post since that's not what ppl are arguing. People are not arguing 'Z is not UP' but saying that the 'OP's data' is not support this and people should not conclude 'Z is UP' by looking at OP. Let's look at it this way, if you take Morrow (who had won A LOT) out of the equation, the Terran win goes down significantly to the point Terran has less win than Protoss or even Zerg. That itself should tell you that the data provided does not say anything about the current balance. I am sure there are other data (though quite small) that could say 'Z is UP' but the OP's data does not say anything and that's what rational people on this topic are arguing about. An irrational person would be arguing NO THIS SUPPORTS the data 'Z is UP' look at those numberz. People aren't lawyers but people will argue if someone calls an orange, an apple.
you can't just "take out morrow's wins", because if he hadn't won, another Terran may of.
How many Zergs do you think were in the finals that he did win? Probably not many.
And look at that post earlier about recent tourneys... in like the 3 most recent tourneys all top 4 spots were Terran.
So its not like eliminating Morrow is really going to change anything.. just a different Terran thats going to win.
|
On September 29 2010 04:57 gospelwut wrote:
I'm sure this has been mentioned, so I apologize if it has.
It should be noted and always thought about that this is one (incomplete) data set. On its own, this yields no real conclusions or even correlations. To make any assumptions you would need other data sets including but not limited to: (a) distribution of races entered into said tournements (b) a metric for judging skill to further polish the numbers (there's no point in including non top players) and (c) some manner of standard deviation or statistical probability -- which is very difficult. Drawing any conclusions from this set of data alone is just as foolish as using Battle.net rankings as a metric of balance.
You are correct that this would be meaningless without other data. Fortunately, that other data exists and is easily available, and the statistical techniques required to analyze the data are not hard.
In order to get an idea of the ratio of Terran, Zerg, and Protoss players in these tournaments, lets use the ratio for the top 100 players in diamond.
http://sc2ranks.com/stats/league/all/1/100/
They are not the exact players, but those players are all probably of the caliber required to be competitive in these tournaments, and all we are looking for is an idea of how many players were from each race. It seems unlikely that this subsection gives bad results, since we see the same basic ratio that exists throughout the ladder.
So, from that data we expect about 23% of the players to be zerg. If we assume that they are all equally competitive (assuming that one group is less competitive would automatically make the conclusion true), then the expected value for the proportion of zerg wins is 0.23.
Now, we can conduct a standard one proportion z test as someone might learn about in any High-school statistics class. I believe most graphing calculators have this function built in (which is how I will do it) and a quick google search will acquaint you with it if you haven't heard of it.
The P-value I get from the test is .0001026. This is very small. It means, basically, that we can be 99.9897 percent sure that zerg players could not have a win rate this small through random chance if the three races are equally balanced. Statisticians normally use 95% as the cutoff for whether the data is conclusive, so I would say that we can indeed draw conclusions from this data.
edit: If anyone's wondering, the same test gives about the same conclusion for how sure we can be about Terran's win rate being higher than expected. The difference between the Protoss win rate and its expected value is not statistically significant. And, if anyone has a more accurate way of determining the proportion of races for only the players who actively compete in tournaments, that would be the best way of ensuring the accuracy of these results.
|
The OP needs to be updated to reflect recent results like the TL open.
|
On September 29 2010 15:08 Count_Waltz wrote:
Either zerg doesn't win tournaments because they're UP or no one plays zerg because they're UP. What are you arguing?
If I'm a new player who's never played SC1:BW, after playing SC2:WOL, I only know how to play T or P, because in the campaign, I never touched a Z. I know how to build buildings, train units with T or P, I have no clue how to do that stuff with Z. I don't know what creep tumor is, what lavas are, and stuff. That is why I don't play Z.
Putting the balance thing aside, it's normal that majority of the players choose T or P. They're exposed to T and P so much after all. I think that's how things work. It's like after GSL, I'm sure there will be a bunch of people switching to Z. It's because they're exposed to high level Z play imo.
|
Is someone going to work on updating this, or do people not think it's worth it?
|
United States22883 Posts
On September 29 2010 15:08 Count_Waltz wrote:
I swear, people who come in here talking about how you need all this additional information such as sample size and correlation etc etc to prove what these results imply. You guys are like lawyers. Arguing about something that is clearly wrong under retarded technicalities. What happened to common sense. You don't need a physics degree to know that coffee coming out the pot is hot. But you accountant and statics majors try to distort the blatant evidence that zerg is under-powered by saying you need more data. gtfo. Either zerg doesn't win tournaments because they're UP or no one plays zerg because they're UP. What are you arguing?
"Common sense" is hardly common. Making assumptions based on weak data is what leads to stuff like "PvZ is unwinnable" circa late 2006. If you want to use statistics, you need to use them well. To be honest, I don't think we should tolerate any more remedial number usages. At best, it's misleading and at worst, it clouds out the bright minds in this community that actually understand how statistics and mathematics work.
|
Socke now has 5 golds
|
United States22883 Posts
On October 03 2010 12:37 electronicJustice wrote:Show nested quote +On September 29 2010 04:57 gospelwut wrote:
I'm sure this has been mentioned, so I apologize if it has.
It should be noted and always thought about that this is one (incomplete) data set. On its own, this yields no real conclusions or even correlations. To make any assumptions you would need other data sets including but not limited to: (a) distribution of races entered into said tournements (b) a metric for judging skill to further polish the numbers (there's no point in including non top players) and (c) some manner of standard deviation or statistical probability -- which is very difficult. Drawing any conclusions from this set of data alone is just as foolish as using Battle.net rankings as a metric of balance. You are correct that this would be meaningless without other data. Fortunately, that other data exists and is easily available, and the statistical techniques required to analyze the data are not hard. In order to get an idea of the ratio of Terran, Zerg, and Protoss players in these tournaments, lets use the ratio for the top 100 players in diamond. http://sc2ranks.com/stats/league/all/1/100/They are not the exact players, but those players are all probably of the caliber required to be competitive in these tournaments, and all we are looking for is an idea of how many players were from each race. It seems unlikely that this subsection gives bad results, since we see the same basic ratio that exists throughout the ladder. So, from that data we expect about 23% of the players to be zerg. If we assume that they are all equally competitive (assuming that one group is less competitive would automatically make the conclusion true), then the expected value for the proportion of zerg wins is 0.23. Now, we can conduct a standard one proportion z test as someone might learn about in any High-school statistics class. I believe most graphing calculators have this function built in (which is how I will do it) and a quick google search will acquaint you with it if you haven't heard of it. The P-value I get from the test is .0001026. This is very small. It means, basically, that we can be 99.9897 percent sure that zerg players could not have a win rate this small through random chance if the three races are equally balanced. You haven't defined what constitutes a balanced race, and you've ignored all external factors. So far you've been able to use numbers to find that a problem exists (Zerg does not win as often as it should in an ideal game state) but you can't recommend corrective measures from that because everything else is still unsolved. If the only map available was Scrap Station, what would the numbers then reflect?
|
Honnestly, LOL @ Zergs.
I really hope to see more Z win soon.
User was temp banned for this post.
|
On September 29 2010 15:08 Count_Waltz wrote:
I swear, people who come in here talking about how you need all this additional information such as sample size and correlation etc etc to prove what these results imply. You guys are like lawyers. Arguing about something that is clearly wrong under retarded technicalities. What happened to common sense. You don't need a physics degree to know that coffee coming out the pot is hot. But you accountant and statics majors try to distort the blatant evidence that zerg is under-powered by saying you need more data. gtfo. Either zerg doesn't win tournaments because they're UP or no one plays zerg because they're UP. What are you arguing?
lmfao are you kidding me? yeah, let's ignore statisticians who for many years have specialized in how you can logically draw conclusions from data through mathematical rigor, and just go ahead and draw fallacious conclusions. i bet you are the same kind of person who doesn't believe in evolution because "it just doesn't make sense that we came from monkeys."
|
|
|
|
|
|
EPT
