|
On April 26 2011 02:00 buldermar wrote: Firstly, I want to point out that I'm taking a mathematical approach to my question.
(...)
Finally, who are you to decide the level of seriousness for the entire community?
...
It's not about a level of seriousness of the community. It's about wether what you're doing is actually credible at all or if it's all just bullmath.
|
On April 26 2011 03:21 Day[9] wrote: Does anyone have statistics on the overall race usage percentage?
Something like
"40% of people who own SC2 play Terran on ladder."
I certainly know that, for new players, there's a skew towards Terran / Protoss as the single player campaign introduces both of those races, but not zerg.
http://www.sc2ranks.com/stats/league/all/1/all
This shows race distribution in leagues. If you scroll down, it also shows win% distribution and avg points distribution for races specifically for GM's.
http://www.sc2ranks.com/stats/league/all/1/100
This shows the same, but solely for the top 100 players. This means that if you scroll down, you'll see the same distributions but solely based on the top 100 of GM.
You can see the same for each of the other leagues, but it has little to no relevance to what I'm looking at in this thread.
I hope it answered your question.
|
On April 26 2011 02:26 TheBB wrote:Show nested quote +On April 26 2011 02:24 strongandbig wrote: First, the sample size of [top10] or [top30] is not big enough that you would expect it to be equal in the absence of imbalance. Over a thousand players, you can safely assume that the distributions of skill and race choice are independent. However, with ten players it's not unreasonable that there are just more Terran players of high skill. Again, some genuine statistical analysis would quantify this for you. There's no need to go around guesstimating which sample sizes are big or small enough.
Same goes here. The sample size the OP uses is the size of the population intended to be examined: the GM league. Thus we don't need to test wether his data is large enough, since by nature of the study, it's all the data that exists. T-, chi-, F-tests ect. are useful if we work with an incomplete set of data. But to my understanding, the data is not incomplete in this case.[/QUOTE]
I took the freedom of highlighting this post as it is well worded and takes on something that many in this thread are skeptical about. Thank you for pointing this out.
|
On April 26 2011 03:29 4of8 wrote:Show nested quote +On April 26 2011 02:40 KillerPlague wrote: There currently is 1638 players listed in GM. The distribution is: 2.6% random 38% protoss 30.3% terran 29% zerg
being a protoss player myself, it's a little hard to ignore how many protoss actually made it in to GM. considering this is the top 200 cumulative for each region it feels like your statistics are biased to make terran seem worse than they are. however, this may be due to the simple fact that more people play protoss? as far as terran dominating the ladder, i think it is due to the relative safety they have. zerg players must scout like hell, protoss players must adapt their composition, terran players can do the same build over and over again vs either race with relative safety. things like salvageable bunkers add to this, as many good players will opt for them when they are not sure. The point is under this 1638 players are players from all Servers and if you look at each server you will see Protoss is dominating the weaker Servers like China ( game was released only some weeks ago => obvious one of the weaker servers at the moment) or Latin America.. but in Europe and Korea terran takes the lead. But this imbalance discussions are really funny. Like in the recent past everybody is saying toss is dominating the big tourneys and then I take a look on the CODE S and CODE A results or the GSL WC and it is not really looking good for toss. And then comes always the quoting of the progamers, but if you haven't mentioned it yet, they are always saying their race is up. Look at guys like Idra, he would even say Zerg is up if they would have 10 Zergplayers in the Top Ten. For some of these guys it might be only the fact, that they are searching for a easy excuse. But I think the main reason is, Blizzard said on the Blizzcon, the opinion of the progamers would be one part of balancing the game. So ask yourself would you really tell the public, if you are thinking your race is op? Even if we would have a p-value under 5% for this stats. This wouldn't mean Toss is up or Terran op. This game is still very young and the patch still new... the only thing we could say that certain strats are at the moment strong or not strong. And with this stats it seems like terrans have at the moment maybe the best working strats for these ladder maps. But nobody knows if this will change in the next weeks even without a patch.
Firstly, this is not a balance debate but a seach for alternative explanations to that 'perspective'. The fact that the game is young does not conflict with my desire of improving on my insight and undertanding of the current ongoing dynamics of the top of the ladder.
And to answer your moral-related question - Yes, personally I would, but I can also see why some would feel inclined to not tell the public.
|
On April 26 2011 16:46 buldermar wrote:
Anyway, what I'm mostly interested in is the top spots, not GM altogether, and why these topspots are being overrepresented by terran players.
one thing you have to look at that i believe you have neglected (probably unintentionally) is the ratio of match-ups i.e. in what match-ups do these top terrans receive their highest win ratios and what the ratio of the match-ups is. if these particular Terran's best match-up is TvP and those are the most frequent match-ups that are played on the ladder (which would statistically make sense since most of the people at the top of the ladder are P), then their overall win percentage would most likely be higher than that of a P who's best match-up is PvZ (lulz) where he wins around 70& of games, *Numbers hereafter are made up solely for hypothetical situation* Imagine this there is a terran that rolls these percentages of each match-up: gets vP: 50% gets vT: 40% gets vZ: 10%
now his best match-up is vP so his win rate is ~70% vP he's okay vT so win rate is ~55% and he just cant figure out vZ consistently so win rate ~ 40%
his overall win rate for all combined would be roughly 165/300 or ~55 percent BUT that doesn't accurately show his win rate because vZ is only 10% of total games so adjusted for race encountered %, the win rate would be more like 63% [ 4/10 vZ 22/40 vT 35/50 vP 63/100 total ]
now lets look at his protoss buddy: his best matchup happens to be vZ (duuur): ~80% he knows vT but gets beaten because of Bo loss(reactor vikings when going colls etc: ~50% and his vP is the "coinflip" that everyone know and loves, he's just a little better at it: ~55%
his overall win rate is 185/300 or ~ 62 perent : more then terran buddy But lets account for race encountered again, it becomes ~ 56% [ 8/10 vZ 20/40 vT 28/50 vP 56/100 total ]
i believe, and i may be wrong, that it is this adjusted percentage that is calculated and shown for ladder rankings. thus putting more terrans who are good at vP ahead of most Ps and putting Z's who can hold there own to Ps around the same tier as the top Ps.
of course my match up encounter 5s are probably way of the mark( I don't think for a second its 33% each though), but these numbers arejust to show you what i mean.
|
On April 26 2011 03:45 TheRabidDeer wrote: I am curious if the numbers will change much when HotS comes out though.
What is HotS?
|
On April 26 2011 18:05 buldermar wrote:Show nested quote +On April 26 2011 03:45 TheRabidDeer wrote: I am curious if the numbers will change much when HotS comes out though. What is HotS?
Heart of the Swarm.. the first SC 2 expansion
|
On April 26 2011 18:05 buldermar wrote:Show nested quote +On April 26 2011 03:45 TheRabidDeer wrote: I am curious if the numbers will change much when HotS comes out though. What is HotS?
Heart of the Swarm, the first expansion for StarCraft 2.
|
On April 26 2011 18:05 buldermar wrote:Show nested quote +On April 26 2011 03:45 TheRabidDeer wrote: I am curious if the numbers will change much when HotS comes out though. What is HotS?
Heart of the swarm, the coming expansion pack for sc2.
Looking at these statistics all I can conclude is that they are inconclusive, not only that but I dont think ladder rankings are a very strong indication of balance.
|
No, you are wrong. Have you ever taken a statistics course? There is always variation in a sample due to pure stochastics. When you flip a coin 100 times, the odds of it landing heads exactly 50 times are actually quite small. Same logic applies here, you have to test what amount of deviation from the norm is actually due to randomness with 90/95/99 percent probability.
|
On April 26 2011 03:55 Roblin wrote:Show nested quote +On April 26 2011 02:11 buldermar wrote:On April 26 2011 02:08 lilky wrote: So basically... Races in order of most played to least played: Protoss, Terran, Zerg
Races in the Top (Insert any number here) in order of most to least: Terran, Zerg, Protoss
TLDR: Protoss is underpowered.. WHAT?!?!?!!?!?!? Correct, that's my overall conclusion based on the observations I made and I'm open for expanding on those observations if anyone thinks I'm being biased. hey bulder, don't say that that is your overall conclusion, step one is to validate his claim. his first premisse: "Races in order of most played to least played: Protoss, Terran, Zerg" correct, this is what his statistics show his second premisse: "Races in the Top (Insert any number here) in order of most to least: Terran, Zerg, Protoss" correct only for top 10, 20, 40 and 50 in the case of top 30, 60, 70, 80, 90 and 100 it is (from bulders statistics) Terran, Protoss, zerg. his conclusion: "TLDR: Protoss is underpowered.. WHAT?!?!?!!?!?!?" since the second premisse is false, no correct conclusion can be made using this information, to lilky I say: L2statistics. edit: I am not saying lilky is wrong, I am not saying lilky is right, I am just saying that the above described line of logic that lilky used is invalid.
Invalid when looking into each individual sample, valid when looking at is as a whole, which is why I put in the word "overall". I didn't intend to respond to the last part about Protoss being underpowered as this isn't a thread about balance/imbalance. I thought that was obvious.
Thank you for looking into it. In particular, I did not take the time to look into his 2nd premisse, which would have been preferred in terms of giving an accurate reply to his, and now that you point it out I probably should have.
|
I feel like these statistical analyses don't really help. A good new strategy/idea on a map for any race could skew the results to favor that race immensely. Then two weeks later the other races adapt and the statistics goes back to more normal figures.
|
On April 26 2011 17:40 buldermar wrote:Show nested quote +On April 26 2011 02:58 Nerski wrote:On April 26 2011 02:11 buldermar wrote:On April 26 2011 02:08 lilky wrote: So basically... Races in order of most played to least played: Protoss, Terran, Zerg
Races in the Top (Insert any number here) in order of most to least: Terran, Zerg, Protoss
TLDR: Protoss is underpowered.. WHAT?!?!?!!?!?!? Correct, that's my overall conclusion based on the observations I made and I'm open for expanding on those observations if anyone thinks I'm being biased. So what you're saying is this is a balance QQ with a clever 'statistical look' to it? Someone lock this sham of a thread, you're not even using statistics correctly just listing out the fact there is more terran on top then toss or zerg. For any statistic to be truly significant the deviance needs to be high enough. Not to mention GM doesn't even represent loads of the actual top players, just the top players who ladder a lot. So there is plenty of margin for error in any statistical breakdown of the GM league. No. As I believe I've mentioned, my intentions with the thread is to cast light on what could be the explanation to why terran players are currently being more dominant than other races on the top of the ladder. This is not a balance debate. Nobody forces you to read the thread. It if doesn't fit your spectre of interest, simply open a new thread. I havn't violated any of the guidelines and was careful not to do so. I don't believe any of the guidelines states that I have to use statistics in a certain way. I also believe that I am free to discuss something even if it leaves room for a margin for error in it's statistical breakdown.
Statistics is a science, that means there's rigor in how statistical tools are used, and one can judge objectly when it is used incorrectly. Nearly every post in this thread (that's not yours) points to the fact that your usage of statistics are incorrect, misleading, or blatantly ignorant of basic principles (which in my eyes, are a sacrilege and affront to numerics). This is not your forum, you don't get to post bullshit just because you feel like it. Furthermore, it's unacceptable to bump your own thread fifteen times within a two hour period. I was also new to TL once, but back then I understand how to show restrain until I familiarize myself with the rules, something you obviously didn't do.
|
On April 26 2011 18:19 karpo wrote: I feel like these statistical analyses don't really help. A good new strategy/idea on a map for any race could skew the results to favor that race immensely. Then two weeks later the other races adapt and the statistics goes back to more normal figures.
Indeed, still though, I believe it's quite interesting that P seem to be doing really well in big tournaments while these stats do at least tell that T is doing really well on ladder. I believe several of the reasons for this have already been brought up. I personally think that salvageable bunkers, the ability to play very defensively and the amount of different cheeses play a big role. Also of course as some have brought up, the lesser games against a race you play, the less those % will be shown in the big picture. Would be really cool to have stats such as, XvP, XvT, XvZ and XvX. Would greatly increase the information able to be gathered from the numbers.
|
On April 26 2011 04:36 Silfurstar wrote: With minimal statistics comprehension, you should realize that a because there is a majority of P players in GM, it means they play more against each other, therefore averaging their own race's win rate. You should have considered P's ratio against T and Z in your analysis.
Although it is unlikely, it could be that the matchup system works so that you're facing an even amount of players from each respective race undependant on how many players that you can be matched up against are playing these respective races. Because I cannot rule this out due to lack of insight in how the matchup system works, I cannot justify accounting for it.
|
On April 26 2011 04:54 zarepath wrote: I've got some stats for you:
My research indicates that the least popular race in the Bronze League is Zerg. Doesn't that mean that Zerg is terribly OP if it's less likely to be horrible?
That's backwards, so no.
|
On April 26 2011 05:23 Raid wrote: This is not a good statistical analysis I think your just trying to look for a pattern. All your are doing is taking numbers and showing correlations that prove absolutely nothing. Its like almost saying that more crimes occur in the summer and more ice cream sales also occur in the summer. So due to the statistics crime and ice cream sales have a direct correlation.
It seems like your just looking into trolling and causing a muck in the community for your own selfish personal reasons. Everyone knows statistics doesn't mean anything on ladder and the tournaments show that too. If statistics hold true to their meaning then the top players on ladder should have been winning tournaments left and right which is not the case.
The game is still being developed and statistics don't mean crap on something that is being developed. For all we know we could be playing the game completely wrong 1-2 years down the road from now.
Scientific evidence does not work on something as volatile as sc2 ladder nor tournaments so please people need to just can it with the statistics.
Thank you for sharing your thoughts. I don't think what I'm doing is a fallacy, whereas your example clearly is.
What it seems to you is far from my intentions. Statistics are not dependant of what they are used on - only how they're interpreted is. My question is specifically related to the top of the ladder, I'm not interested in discussion the correlation between rank on ladder and likelyhood of winning a tournament.
The game is still being developed, but that does not keep me from wanting to improve on my understanding of its current dynamics. I don't know why this is so difficult to comprehend.
|
|
On April 26 2011 05:49 Pelican wrote:Show nested quote +On April 26 2011 02:02 Shaetan wrote: You can't claim to do statistical analysis then just throw out numbers and claim that X is true, you have to do the analysis. This... Show nested quote +On April 26 2011 02:25 dogmeatstew wrote: All the win %'s are very close. The average number of points is very close, 15 points isn't a lot and as you've already stated, a large amount of top 10 is terrans which would easily skew this.
In short I'm not sure how these numbers give you the impression that terran is dominating in every area, a 2% higher win ratio isn't statistically significant even across 1638 players and all in all this last set of data actually looks pretty even across the board to me. ...and this. Let me start by saying that I don't think it's very useful to try and statistically analyze the current state of balance based off of the Blizzard ladder. I just want to make a point that if you're going to attempt using statistics, you should actually use statistical analysis and not just look at numbers and try and determine if patterns exist -- this doesn't work and this is why the field of statistics exists.
I am not trying to analyze the current state of balance based off of the Blizzard ladder, merely trying to understand the top of GM is overpresenated by terrans. While what you're doing works for a single sample of data, it does not look into multiple areas and their interrelation.
On April 26 2011 05:49 Pelican wrote: I'm not a statistician, just a lowly science grad student, but I did some really, really simple stat analysis on the North American Grandmaster league statistics (it would take a really long time to gather the data from every league into Excel). If you just look at the data (like the OP) did, it seems like there are some differences here:
Win% by race: P: 59.0% (15,632) T: 61.4% (10,083) Z: 59.7% (11,163) R: 55.4% (1,333)
You should probably do it on top 100 or top 200 of GM rather than specifically on NA GM. SC2ranks.com allows for showing this data listed the same way that NA GM is listed.
On April 26 2011 05:49 Pelican wrote:
But you can't really tell if there is or not without actually analyzing the data. So I ran a one-way ANOVA on the NA GM league, comparing win% between the races. All the data were pulled from SC2Ranks. The data weren't normal, so a square root transformation was applied [automatically, by the program] to meet the assumptions of normality for ANOVA. The assumption of homogeneity of variances was also met (p=0.430).
This method does not account for the likelyhood of having multiple samples show the same trend. It solely looks at any one group of players, some variables related to them (i.e. win%, points, etc), and if the trend you're looking at is inside or out of the 95% confidence interval. (I do not know the english words, so I can only hope my point is still clear)
On April 26 2011 05:49 Pelican wrote:Here is the descriptive statistics table generated: From just this table, you can see that the 95% CIs overlap between every race. Note that the mean values are the actual values, not the sqrt transformed values (not sure why the program does this). The ANOVA table: This shows that there is a statistically significant (p=0.043) difference overall between the group means, but it doesn't tell us where the differences are. This is where post-hoc tests are important, as they lets us look at comparisons between multiple groups: Link for Big! Here, we have two post-hoc test results. In this table 1=P, 2=T, 3=Z, 4=R. We can see that in the Tukey test, there is a marginally significant difference between T and P win%s, and the Least Significant Difference test shows that there is a significant difference between T and P. Essentially, what we glean from this entire test is that the only real differences in win% are between Terran and Protoss, and that difference is pretty small. To visualize the actual comparisons, here is a bar graph with ERROR BARS! TL;DR: Analysis of variance shows that the only difference between NA GM win%s is in T and P -- and it's not very big. Don't make threads about taking 'mathematical' approaches or statistical comparisons if you're not going to actually use statistics. Looking at numbers =/= statistics.
The difference shows a less than 5% chance of it being due to variance/coincidence. Add to that the fact that you've only made this statistical analysis on one sample, and that this sample is NA rather than the actual top 200 of GM. I'd say that this supports what I reached with my approach more so than it conflicts it. You can't just do your 95% confidence interval analysis and then 'ignore' the fact that T-P is out of that interval.
If you're up for it, I'd be interested in what a similar analysis would show of only top 100 GM. Here is the link; http://www.sc2ranks.com/stats/league/all/1/100
If you have a link to a free version of the program you're using, I'll do it myself.
Also, what analysis method would you recommend for showing the confidence interval of the amount of terran players in the respective intervals of 10, accumulative (top10, top20, top30 etc) in relation to the total amount of terran players in GM? Is there a way around doing each group seperately?
|
On April 26 2011 06:13 azn_dude1 wrote: Points only mean how often you've played, which means nothing. Nothing at all. Win ratio means nothing when you've played only 7 games. Terran win percentage is barely greater than the others, but that could just be because there are more terrans, resulting in tvt being the most common mirror matchup.
This post means nothing at all, it's just some statistics that are misleading.
Except for the fact that there is only about 30% terrans in GM. If my post means nothing, where does it put yours?
|
|
|
|