BuzzerBeater Forums

That is both very interesting and very bizarre.

Well, like I said, the model is far from complete. But it seems that if I can keep the hype going, more people will want to participate. So I would certainly not accept any statement I make at the moment to be the truth. At least... not yet. ;-)

For example, the model says my HOF SF trainee is capped, but I sincerely doubt that he is.

They are just interesting results for the moment.


Last edited by HeadPaperPusher at 8/30/2010 10:08:40 PM

There is a player on the TL now with high lvl in driving and handling and it seems they've an influence on the salary (cap)

How exactly do you know a player capped? He doesn't pop like for four weeks of same skill training? Or he "refuses" to pop in any skill if you train him?
EDIT: Oh, and btw, you started an excellent "test", imo. We still don't know many things about BB and the thing I'm most interested in (beside game engine, of course) is how is potential linked to skill capping. I have a 6th man potential that I want to train to 15k salary, but I don't know if I can. And btw, if you look at transfer list with certain criteria (for example, jump shot min sensational and potential max 6th man), I think you can find interesting results.

Last edited by Koperboy at 8/31/2010 3:21:03 AM

Very good question of Koperboy.
How do you identify players which have just reached cap and players long way after being capped? Because there are plenty of players which have had some (or even quite a lot of) pops after being capped. I think very important for this analysis is to catch just the moment of capping.

.
How do you identify players which have just reached cap and players long way after being capped? Because there are plenty of players which have had some (or even quite a lot of) pops after being capped. I think very important for this analysis is to catch just the moment of capping.

I agree. That's why I am generally only taking players from teams who can give me a fairly good recent training history on their player. I am not just taking players off the TL, as there is no way to know if the player is capped or if they received training after capping.

There are some players that I am not sure of. Either because the owner could not remember the exact skills or because their training history is vague. There is also one case (RIP's player Abbott) where I do not know 100% if he is capped, but I put him in the model anyways. But if I ever have enough data, I should be able to drop these players if I keep good notes.

I will admit this: the truth is that I cannot wait for perfect players to do this analysis. I also have to take a leap of faith and trust the people who send me data. That may introduce some error or bias into the model. But I do not see a way around this.

Excellent job!!!
I´m going to follow this thread.
go on!!!


Last edited by Seba at 8/31/2010 6:52:58 PM

I have changed my modelling technique. Instead of continuing with logistic regression, I am going with a total least squares approach instead. For those serious number crunchers out there, see: (http://en.wikipedia.org/wiki/Total_least_squares).

Why change the approach? Well, I am a bit worried about the error in this model. In particular, this should satisfy those who belive in the potential sub-levels theory since it allows for error in both the response and dependent variables. I can now drop that assumption from my (long) list of assumptions. It is certainly more complex but that is another story.

In any case, in order to program this I had to go back to my university days and re-learn non-linear programming. This allowed me to put certain constraints on the model parameters (so, for example, no coefficient becomes negative, which I was having a problem with under logistic regression).

I would still like to put additional constraints but I think I have reached the limit of my skills. If anyone knows anything about non-linear programming, and in particular how to program it in SAS, please contact me.

Sorry for the long-winded details, I will be less technical in the future. ;-)

Now, I bet you are all wondering how this new approach changes the model. To be honest: not much. I mean, the parameters change and I must admit that the model now seems to do a better job in general. But shockingly, the outside defense contribution is still zero! Same goes for driving, it is not contributing anything to capping in the current model (although that is not necessarily a surprise, since it is linked to handling and handling is now contributing more).

The other parameters have a bit more of a contribution now, most notably passing and handling.

While I like this approach a lot more, it still needs the data to do a good job. So please continue to send data. ;-)

of which by far the biggest, in my view, is that the cap coefficients are the same independent of position.

I am putting position in the model (as a class varible) but as I said before (I think I said it, anyways), the effect is pretty small, so I drop it from the final model. But I will keep testing it. If and when I get enough data I should be able to determine if indeed the formula needs to be split (like you did for salary) or if it still remains insignificant enough to be left off the final model.

Anyhow, a couple of people have mentioned that I should consult with you while I do this. I sort of assumed you would be reading and would comment as necessary. So please do - I welcome any suggestions you might have.