EPTOn September 14 2013 05:23 Anomi wrote:
I did say sry realising the posts i wrote was a bit to critical and to some extent unnecessary. As for why?
the same reason you posting a critic on someone opinion
.
Just to clarify the work is good and I am just over critical.
Show nested quote +
On September 14 2013 04:27 Cracy wrote:
Why would you even write all the posts? I do understand the constructive criticism but hey... You are now offending the intelligence of all the people who read it and ENJOY IT.
For one thing I work with stats and models for living and still it wouldn't come to my mind to criticize the work done.
On September 14 2013 04:08 Anomi wrote:
It would actually take me allot of time or maybe impossible to figure out on how to create a model that would fill this roll. . Using tools as http://www.r-project.org/ that is free will give you to tools to maybe create a better simulation . Using a logistical model to work with this kind of data might work better but not sure about that (http://en.wikipedia.org/wiki/Logistic_regression).
For now you should just add a similar response from lolfail9001 and state what those cases are “Aligulac just provides CHANCES for player to advance from group that he uses in his simulation to calculate chances of player advancing or not in certain cases.”
It’s still not 100% correct way of saying it but people would probably just be confused if you tried to explain that the chance from Aligulac ranking is a estimation of what the chance can be and not the actual chance the player that is then used in a simulation to predict what the actual chance could be to qualify to Blizcon .
The bottom line is that there is no wrong or right as long as you state the assumption the model is based on and the reasoning behind the decision you made(for instance why using Aligulac ranking as factor and not win ratio ect ). This is the only thing I would actually tell you that needs to be done better.
PS:Sry if i sounded critical is still a nice contribution and well done work
On September 14 2013 02:22 Die4Ever wrote:
Can you give me example source code for this improved model you're asking for? Make sure you factor in how good the air conditioners inside the booths are for each tournament, this will especially affect Huk.
If you're just telling me that my model is not perfect, I already know this. If it was perfect then it wouldn't say Naniwa has a ~20% chance, it would either say 100% or 0%, I would just tell you who qualifies, and then I would go win every bet in every sport ever. If you have constructive criticism then I'd like to hear it.
edit: I don't mean to sound rude, but I think everyone knows what you're saying when they read threads like this. I'm pretty sure they know I can't see the future.
On September 14 2013 02:13 Anomi wrote:
What your missing is that your purely viewing this as mathematical problem. A good model is not based on how well it predicts but how well it predicts when its based on the right assumptions. Your only assumption seems to be that the skill factor (that in the first place is hard to measure) is the only thing that plays in on who qualifies to blizcon. You are discarding allot of stuff. For instance i would guess that according to aligulax invasion should not have lost his group in season 2 finals but he did. Was this because he was less skillful or that he doesn’t handle traveling well or something else.
Let me try to clarify: To be able to create a model that would simulate who would get in to blizzcon or not would almost be the same thing on who would end up being in the playoffs in a sport game. To create that kind of prediction model is allot more complex. for instance if you would do that for ice hockey you would need to create a indicator first for skills if that’s even possible. Then indicators on players physical and mental health . You might also need indicators on the effect on home turf advantage and maybe players.
Try running the simulation based on the wcs rankings instead of Aligulax rankings and see what you end up with and try once more with win ratios instead. If any if these ends up being abel to do better prediction would you say they are better?
On September 14 2013 01:41 Die4Ever wrote:
Yes.
Well almost. It actually does a pretty damn good job of predicting who is locked in for Blizzcon, or who can't possibly qualify, which would be really hard to do as accurately with pen and paper. And it also calculates multiple matches, so if someone needs to win 1 more match against a same-skill opponent(according to aligulac of course) then they get a 50% chance, if they need to win 2 matches against same-skill opponents then it goes down to 25%. Amplify this to full brackets of multiple tournaments and it gets to be a lot of work. Also this tells you what events need to happen for them to qualify.
edit: tld;dr of course it's not perfect, but lots of people seem to like it anyways
On September 14 2013 01:23 Anomi wrote:
My only problem with these kind of things is that even if you can simulate it your still using ordinal data when it comes to using Aligulac rankings (http://en.wikipedia.org/wiki/Ordinal_data).
I don’t think you’re doing the simulation wrong but you’re using data that to begin with that doesn’t actually calculate what player is better than who 100% correct. IT might be better then win ratio but it’s far from being 100% correct.
This is just my opinion but when it comes to calculating simulation based stuff that don’t come as numbers naturally:
The answer the simulation creates is the same thing of just creating a guess that might be better than if you wild guess randomly. IN your case the answer your model will simulate is a guess that might be better then random person guess but it’s still a guess.
My only problem with these kind of things is that even if you can simulate it your still using ordinal data when it comes to using Aligulac rankings (http://en.wikipedia.org/wiki/Ordinal_data).
I don’t think you’re doing the simulation wrong but you’re using data that to begin with that doesn’t actually calculate what player is better than who 100% correct. IT might be better then win ratio but it’s far from being 100% correct.
This is just my opinion but when it comes to calculating simulation based stuff that don’t come as numbers naturally:
The answer the simulation creates is the same thing of just creating a guess that might be better than if you wild guess randomly. IN your case the answer your model will simulate is a guess that might be better then random person guess but it’s still a guess.
Yes.
Well almost. It actually does a pretty damn good job of predicting who is locked in for Blizzcon, or who can't possibly qualify, which would be really hard to do as accurately with pen and paper. And it also calculates multiple matches, so if someone needs to win 1 more match against a same-skill opponent(according to aligulac of course) then they get a 50% chance, if they need to win 2 matches against same-skill opponents then it goes down to 25%. Amplify this to full brackets of multiple tournaments and it gets to be a lot of work. Also this tells you what events need to happen for them to qualify.
edit: tld;dr of course it's not perfect, but lots of people seem to like it anyways
What your missing is that your purely viewing this as mathematical problem. A good model is not based on how well it predicts but how well it predicts when its based on the right assumptions. Your only assumption seems to be that the skill factor (that in the first place is hard to measure) is the only thing that plays in on who qualifies to blizcon. You are discarding allot of stuff. For instance i would guess that according to aligulax invasion should not have lost his group in season 2 finals but he did. Was this because he was less skillful or that he doesn’t handle traveling well or something else.
Let me try to clarify: To be able to create a model that would simulate who would get in to blizzcon or not would almost be the same thing on who would end up being in the playoffs in a sport game. To create that kind of prediction model is allot more complex. for instance if you would do that for ice hockey you would need to create a indicator first for skills if that’s even possible. Then indicators on players physical and mental health . You might also need indicators on the effect on home turf advantage and maybe players.
Try running the simulation based on the wcs rankings instead of Aligulax rankings and see what you end up with and try once more with win ratios instead. If any if these ends up being abel to do better prediction would you say they are better?
Can you give me example source code for this improved model you're asking for? Make sure you factor in how good the air conditioners inside the booths are for each tournament, this will especially affect Huk.
If you're just telling me that my model is not perfect, I already know this. If it was perfect then it wouldn't say Naniwa has a ~20% chance, it would either say 100% or 0%, I would just tell you who qualifies, and then I would go win every bet in every sport ever. If you have constructive criticism then I'd like to hear it.
edit: I don't mean to sound rude, but I think everyone knows what you're saying when they read threads like this. I'm pretty sure they know I can't see the future.
It would actually take me allot of time or maybe impossible to figure out on how to create a model that would fill this roll. . Using tools as http://www.r-project.org/ that is free will give you to tools to maybe create a better simulation . Using a logistical model to work with this kind of data might work better but not sure about that (http://en.wikipedia.org/wiki/Logistic_regression).
For now you should just add a similar response from lolfail9001 and state what those cases are “Aligulac just provides CHANCES for player to advance from group that he uses in his simulation to calculate chances of player advancing or not in certain cases.”
It’s still not 100% correct way of saying it but people would probably just be confused if you tried to explain that the chance from Aligulac ranking is a estimation of what the chance can be and not the actual chance the player that is then used in a simulation to predict what the actual chance could be to qualify to Blizcon .
The bottom line is that there is no wrong or right as long as you state the assumption the model is based on and the reasoning behind the decision you made(for instance why using Aligulac ranking as factor and not win ratio ect ). This is the only thing I would actually tell you that needs to be done better.
PS:Sry if i sounded critical is still a nice contribution and well done work
Why would you even write all the posts? I do understand the constructive criticism but hey... You are now offending the intelligence of all the people who read it and ENJOY IT.
For one thing I work with stats and models for living and still it wouldn't come to my mind to criticize the work done.
I did say sry realising the posts i wrote was a bit to critical and to some extent unnecessary. As for why?
the same reason you posting a critic on someone opinion
.Just to clarify the work is good and I am just over critical.
Well, I think the problem with your criticism is that it appears to lack direction. A model is always a simplification of reality, and your criticism seems to criticize the fact that the models used aren't absolutely accurate, and that isn't really fair.
Demanding reasoning behind all the decisions made isn't really fair either:
"The bottom line is that there is no wrong or right as long as you state the assumption the model is based on and the reasoning behind the decision you made(for instance why using Aligulac ranking as factor and not win ratio ect )."
He clearly states that he uses Aligulac, isn't that enough?
