View Full Version : Any math whizzes on here?

Mogulseeker

12-01-2011, 07:40 PM

I've always thought that if someone could formulate a statistical model for winning based on numbers - everything from using combine results (for bringing in players) to play calling...

Could this be the start of a "statistical" NFL model?

http://blogs.denverpost.com/broncos/2011/12/01/harvard-students-set-out-to-statistically-prove-the-miracle-of-tim-tebow-for-broncos/10979/?source=rsshomeblog

Mogulseeker

12-01-2011, 07:41 PM

Another:

http://harvardsportsanalysis.wordpress.com/2011/11/26/a-statistical-analysis-of-the-miracles-of-tim-tebow/

Bacchus

12-01-2011, 07:46 PM

I've always thought that if someone could formulate a statistical model for winning based on numbers - everything from using combine results (for bringing in players) to play calling...

Could this be the start of a "statistical" NFL model?

http://blogs.denverpost.com/broncos/2011/12/01/harvard-students-set-out-to-statistically-prove-the-miracle-of-tim-tebow-for-broncos/10979/?source=rsshomeblog

You can't base it on numbers because sports are more than numbers. You can not put a number to work ethic, desire or just being a good teammate. Jeff George had great numbers I'm sure.

Mogulseeker

12-01-2011, 07:47 PM

Tebow has a much worse EPA – meaning that he has objectively produced worse results over all of his plays – but a significantly better (though still negative) WPA – meaning that his plays have contributed more to the chances of his team winning. While Tebow’s plays have produced much fewer expected points than Orton’s, Tebow’s positive plays have come at crucial points in the game, when they have a much larger impact on the outcome: think his 20 yard TD run for the lead with 58 seconds left last week, or his 56 yard TD pass for the lead with 6:44 left the week before. Likewise, Tebow’s negative plays have come at points where their effect was less harmful.

EPA - Expected Points Added

WPA - Win Probability Added

cutthemdown

12-01-2011, 07:48 PM

Tebow + Ball / Juice = winning

jet19

12-01-2011, 07:50 PM

I am kind of a math whizz, I took a look at that info and I think I have the formula you are looking for

Tebow+Miller+Elway=Win

Abqbronco

12-01-2011, 07:59 PM

I am kind of a math whizz, I took a look at that info and I think I have the formula you are looking for

(Tebow+Miller+Elway)-orton=Win

Math error corrected. Analysis complete

Mogulseeker

12-01-2011, 08:07 PM

I think the board is more in line with:

[(Von + Doom + Bunkley) x (Champ + Bailey / Goodman)] + {[(Tebow/McCoy) x McGahee] + (-Orton)} = win

The front seven compounds coverage (they play off eachother), Champ and Dawk are divisible by the weakness = Goodman.

Added to...

Tebow, divisible by McCoy's play calling (not my opinion, the forum's ;P). McGahee is independent from Tebow's parenthetical because he can just pound it but Tebow's inability to open up limits McGahee's potential, and adding a negative Orton (addition by subtraction).

About right?

gyldenlove

12-01-2011, 08:07 PM

Ultimately there are far too many variables and far too few games to make a model with any kind of decent behaviour. Simply put the number of input variables is much greater than the number of possible data points (games) which means you can not find anything that even resembles a unique solutions (there will be infinitely many solutions) unless you introduce arbitrary ad hoc contraints the limit the solution space.

In this analysis the choice of input variables is highly questionably as every metric used is highly subjective. EPA for instance fails to take into account the situation you are playing in, if you are facing a very strong defensive team in really bad weather with a lot of injuries on your offense you are not nearly as likely to score points as you are if you are facing a very bad defense with a lot of injuries in a dome. EPA since it is based on historical averages is a metric that entirely negates these much more important factors. WPA is like EPA in that it is based entirely around historical data which washes out trends, some QBs and teams are very good in the 4th quarter (Elway was) and some are very bad (Orton), this means that if Elway had the ball at midfield with 1.11 to go down by 4, he was all else being equal, substantially more likely to pull out the win than Orton would be in the same situation - WPA because it is based on averages fails to take this into account and so Elway would have a surprisingly high WPA when studying his results compared to Orton - this is the same with Tebow, he in many games plays much better in the 4th quarter than he does in the first.

Using DVOA as a metric of how the defense has played is absurd at best, the DVOA metric is highly subjective and includes evaluation of each play and as such has as much to do with whoever is reviewing the game and possibly what that person had to eat as it does football.

Returning to the actual analysis, what it shows is that Tebow is good when it matters the most and not very good when it has the least impact. The author concludes that this is an aberration and therefore not likely to last, however I would say it is a result of the metric failing to account for players who consistently can elevate their game in crunch time and has no predictive value at all. I am sure if you compare different QBs over their careers to the model you will see outliers who are no more extreme than the Tebow case.

But given that Tom Brady and Aaron Rodgers haven’t been able to do that over the long term, I wouldn’t bet the farm on it.

That is not only a poorly written sentence it is also wrong. What has happened is not that Tom Brady and Aaron Rodgers are winning less than they used to, they are scoring more than they used to, so rather than winning more than their production would warrant given his model they are now producing enough for his model to justify their very high win percentages. The Brady and Rodgers examples show that is not only possibly but in fact not particularly unlikely for a young QB to win despite not producing as much as expected.

Bacchus

12-01-2011, 08:24 PM

What would be the numerical rating be for being blessed by Jesus?

Mogulseeker

12-01-2011, 08:27 PM

What would be the numerical rating be for being blessed by Jesus?

Tebow ∞

crawdad

12-01-2011, 08:31 PM

What would be the numerical rating be for being blessed by Jesus?

Your name should be selur wobet to be honest. But the Broncos Rule in my house!

That One Guy

12-01-2011, 08:31 PM

I think the current equation is:

{avg[(Miller's pass rush)+(Doom's pass rush)]-avg[(RT pass block ability)+(LT pass block ability)]}*(opp QB resilience value)/(opp ability to stay awake*[Tebow+McGahee rush success]*(Tebow luck factor)

KipCorrington25

12-01-2011, 08:34 PM

If you need math whizzes try Chiefs Planet... oh wait no, that's meth whizzes on Chiefs Planet I always get that confused.

Mogulseeker

12-01-2011, 08:40 PM

If you need math whizzes try Chiefs Planet... oh wait no, that's meth whizzes on Chiefs Planet I always get that confused.

There are some smart dudes on this forum.

Rohirrim

12-01-2011, 08:54 PM

If you need math whizzes try Chiefs Planet... oh wait no, that's meth whizzes on Chiefs Planet I always get that confused.

Ha!

Vegas_Bronco

12-01-2011, 09:15 PM

Our company does this daily on other market oriented studies and spends millions each year backtesting coefficients...trust me when I say...there will always be outliers anomalies to the model that really make the model more of a probability and speculation tool than an firm investment by which you can guarantee a certain result. I can tell you who is most likely to spend and on what and when but whether that actually happens or not is speculation.

Broncoman13

12-01-2011, 09:22 PM

Tebow + Ball / Juice = winning

I thought juice went to the 10th power???

Willynowei

12-01-2011, 09:31 PM

I've always thought that if someone could formulate a statistical model for winning based on numbers - everything from using combine results (for bringing in players) to play calling...

Could this be the start of a "statistical" NFL model?

http://blogs.denverpost.com/broncos/2011/12/01/harvard-students-set-out-to-statistically-prove-the-miracle-of-tim-tebow-for-broncos/10979/?source=rsshomeblog

There are extremely well paid geniuses who spend their entire life's work trying to predict things with significantly more historical data than the performance of Tim Tebow (and all of the advanced NFL stats they used there); and who have managed to, despite all that, repeatedly **** it all up.

Then you have two guys from a school with a nice name draw a cute graph after guessing at the effect of a few variables on the game of football - a sport full of Chaos - of motorcycle injuries, I-hop related injuries, gun shootings, idiotic actions leading to suspensions, egotistical coaches pulling players to show power, teams running offenses and plays no one has seen before, and a league refereeing committee that comes up new **** to call/ignore every day.

I don't have a Phd in economics from MIT, but I won't need one to tell you that the study those two guys are doing is likely no better at predicting Tim Tebow's future performance than you or me after a dozen shots of Jameson.

EDIT: I feel like i said a whole lot of nothing related to the Topics main question, which seems to be whether the study hints that this style of modeling might be valid for future use etc.,

Answer is no, study looks pretty meaningless to me. All they did was draw a relationship between how many points a QB is expected to add (how they got that i have no idea) vs. the chances of winning the QB adds to a team(how they got that, who knows). Thats two pretty ****ty and arbitrary numbers considering the amount of other factors in a football game, how the heck do you know whether it was the QB that day or the rain? or the offensive coordinator, or receiver/corner matchup? the answer is you can't control for these things and theres likely not enough info on the NFL to get these numbers in the first place.

Also, the R-squared (correlation/relationship they did find) is 82% and thats kind of ****ty, I could probably find stronger correlation between microwave use and erectile disfunction.

Although, i'd be shocked if far better, more complex, and more accurate models didn't exist in the hands of Vegas odds makers.

Requiem

12-01-2011, 09:32 PM

Math sucks.

Vegas_Bronco

12-01-2011, 09:46 PM

Math sucks.

Says the twin brother left on earth that isn't traveling at light speed.

That One Guy

12-01-2011, 10:00 PM

Although, i'd be shocked if far better, more complex, and more accurate models didn't exist in the hands of Vegas odds makers.

Exactly what I thought, too. If the game of football could be predicted, Vegas would have the equation.

theAPAOps5

12-01-2011, 10:04 PM

The problem with using stats to project winners from the draft is that this is a team sport based on 11 players who play as a unit and are dependent on each other. Nearly impossible

broncosteven

12-01-2011, 10:24 PM

I've always thought that if someone could formulate a statistical model for winning based on numbers - everything from using combine results (for bringing in players) to play calling...

Could this be the start of a "statistical" NFL model?

http://blogs.denverpost.com/broncos/2011/12/01/harvard-students-set-out-to-statistically-prove-the-miracle-of-tim-tebow-for-broncos/10979/?source=rsshomeblog

I just read where SpaceX did a model on their rocket engine (The Merlin) and they found that by feeding the fuel in a stream through a needle like injector rather than the traditional "shower head" injector plate format they got better performance and less chance for combustion instability (this is the one issue that troubled Von Braun's team and lead to the shower head config) than current liquid fueled rockets.

Math and Science stuff is fun.

I've always thought that if someone could formulate a statistical model for winning based on numbers - everything from using combine results (for bringing in players) to play calling...

Could this be the start of a "statistical" NFL model?

http://blogs.denverpost.com/broncos/2011/12/01/harvard-students-set-out-to-statistically-prove-the-miracle-of-tim-tebow-for-broncos/10979/?source=rsshomeblog

I worked those models about 20 years ago. You can beat the spread reliably. But by such a small amount that you would have to have a lot of money and patience to have a reliable winning strategy over the long run. The reason, you would have to be able to stand up to several losing weekends in a row.

BroncoMan4ever

12-01-2011, 11:36 PM

I've always thought that if someone could formulate a statistical model for winning based on numbers - everything from using combine results (for bringing in players) to play calling...

Could this be the start of a "statistical" NFL model?

http://blogs.denverpost.com/broncos/2011/12/01/harvard-students-set-out-to-statistically-prove-the-miracle-of-tim-tebow-for-broncos/10979/?source=rsshomeblog

it is impossible to gauge talent based on the measurables and numbers.

you can't put a number on a player's heart, desire, or any of the intangibles that a player would use to tread the line of elite player or draft bust.

every year guys who have the insane measurables and seemingly the talent that makes scouts drool, fall flat on their faces, while overlooked guys with questionable measurables, become stars.

in the end the draft is a guessing game.

uplink

12-01-2011, 11:48 PM

Just don't divide by Orton and you should be defined.

vonqkilla

12-02-2011, 12:02 AM

Any Meth whizzes around here?

I searching for any chief fans left and I need bait.

ColoradoDarin

12-02-2011, 06:21 AM

This is why it's more fun to play FPS against humans than bots....

Broncomutt

12-02-2011, 06:46 AM

Just don't divide by Orton and you should be defined.

Ørton

Punisher

12-02-2011, 07:26 AM

I really great at math and numbers but i suck at english

Kaylore

12-02-2011, 07:55 AM

I'm not to crazy with his projections. He's using Vince Young as a control...

gyldenlove

12-02-2011, 08:25 AM

I worked those models about 20 years ago. You can beat the spread reliably. But by such a small amount that you would have to have a lot of money and patience to have a reliable winning strategy over the long run. The reason, you would have to be able to stand up to several losing weekends in a row.

Beating the spread is more about psychology in a lot of cases than statistical modeling, the spread is calculated to account for betting trends to minimize house liability, so you need to find the games where betting trends move the spread away from the purely anticipated result and hit those very hard, at least that is my experience.

Mogulseeker

12-02-2011, 06:35 PM

Question: what would a "statistical model" playbook look like?

What would a "physical model" scouting model look like?

Von Miller's ability to run through RTs that are literally 100lbs heaver than him defies the laws of physics...

Bronx33

12-02-2011, 06:56 PM

Tebow + Ball / GOD = winning

Fixed

broncosteven

12-02-2011, 07:16 PM

Question: what would a "statistical model" playbook look like?

What would a "physical model" scouting model look like?

Von Miller's ability to run through RTs that are literally 100lbs heaver than him defies the laws of physics...

Don't coaches already use Statistical models when calling plays by down, distance, and place on the grid Iron in their playbooks?

Not sure what a physical model scouting model is.

Yes Von Miller is the random variable that skews the models and is the reason why they suit up and actually play the games.

You ever played stratomatic baseball?

gyldenlove

12-02-2011, 09:45 PM

Question: what would a "statistical model" playbook look like?

What would a "physical model" scouting model look like?

Von Miller's ability to run through RTs that are literally 100lbs heaver than him defies the laws of physics...

Actually it is good physics, in any isolated collision momentum is conserved, since Miller has solid bulk and carries a lot of speed he has a lot of momentum, there are only two ways for an offensive lineman to stop him, one would be for the lineman to carry momentum in the opposite direction to cancel out Miller's momentum and the other is to use a lot of friction with the ground to ensure that the collision is not isolated and the momentum can be wasted into friction - the first suggestion is of course impossible as you will never see a RT in pass protection run at the defender, so the only thing you can do is anchor as hard as you can, but with Miller's quickness if you just set your feet he will run around you in a heartbeat.

A statistical playbook already exists, those sheets you see offensive coordinators carry around have plays listed for any situation, 2nd and short, 3rd and short, 3rd and long, red zone, own goal line etc. On 3rd and short you will usually not try to pass an intermediate route, you either go for the safe short gain or try for the long gain.

Scouting can't be done by numbers, there is not a single observable that correlates with success and no compound metric of many observables can truly capture the potential of a player. Look at Champ Bailey, the key to his success is his speed and quickness, because of his supreme athletic ability he is able to spend a lot of time looking at the QB and looking for the ball because he can't be beaten in a foot race - on the other hand Chris Houston who is also a hugely fast CB has not anywhere near the same success. Succesful scouting is a combination of luck, knowing what you need in a player to succeed for your situation and not getting blinded by one factor - it is too often too easy to be blinded by speed or huge production or size or strength.

Mogulseeker

12-02-2011, 10:38 PM

Actually it is good physics, in any isolated collision momentum is conserved, since Miller has solid bulk and carries a lot of speed he has a lot of momentum, there are only two ways for an offensive lineman to stop him, one would be for the lineman to carry momentum in the opposite direction to cancel out Miller's momentum and the other is to use a lot of friction with the ground to ensure that the collision is not isolated and the momentum can be wasted into friction - the first suggestion is of course impossible as you will never see a RT in pass protection run at the defender, so the only thing you can do is anchor as hard as you can, but with Miller's quickness if you just set your feet he will run around you in a heartbeat.

A statistical playbook already exists, those sheets you see offensive coordinators carry around have plays listed for any situation, 2nd and short, 3rd and short, 3rd and long, red zone, own goal line etc. On 3rd and short you will usually not try to pass an intermediate route, you either go for the safe short gain or try for the long gain.

Scouting can't be done by numbers, there is not a single observable that correlates with success and no compound metric of many observables can truly capture the potential of a player. Look at Champ Bailey, the key to his success is his speed and quickness, because of his supreme athletic ability he is able to spend a lot of time looking at the QB and looking for the ball because he can't be beaten in a foot race - on the other hand Chris Houston who is also a hugely fast CB has not anywhere near the same success. Succesful scouting is a combination of luck, knowing what you need in a player to succeed for your situation and not getting blinded by one factor - it is too often too easy to be blinded by speed or huge production or size or strength.

So what is the percentage that a defense doesn't play the intermediate zone?

mwill07

12-03-2011, 06:50 AM

If playcallimg was built on sound statistical models, I think there would be far fewer punts.

Cito Pelon

12-03-2011, 03:25 PM

The "IT" factor screws everything up mathematically.

gyldenlove

12-03-2011, 03:41 PM

So what is the percentage that a defense doesn't play the intermediate zone?

The reason you wouldn't throw an intermediate pass is because the defense will often be very aggressive at the front with a run blitz and often tight coverage on the outside, so the passer often will not have a lot of time to throw which takes the intermediate passes out of the equation since with on coverage you can't create a lot of seperation quickly - basicly some forms of defense counter some forms of offense very well and one thing that is quite well countered by a defense meant to stop run plays and short passes is medium passes.

The most open down is 2nd and short followed by 1st and 10. On 2nd and short the defense has to choose between trying to stop the run for a 1st down or the big pass play, this means as an offense you can try to guess which they are going for and counter it, but it will always be a guess - some times they may go cover 3 with underneath zones and your screen play is going to come up lame in that situation, on the other hand your delayed handoff with a pulling offensive lineman may gain a ton of yards - on the same down they could go run blitz with man on the outside in which case your screen may work like a charm but your delayed handoff gets stuffed in the backfield. You can play the odds of course by what a defense has done previously in similar situations, but really it is like switching your pitcher depending on what side of the plate a batter swings from, it only buys you a few %.

Mogulseeker

12-03-2011, 04:13 PM

The reason you wouldn't throw an intermediate pass is because the defense will often be very aggressive at the front with a run blitz and often tight coverage on the outside, so the passer often will not have a lot of time to throw which takes the intermediate passes out of the equation since with on coverage you can't create a lot of seperation quickly - basicly some forms of defense counter some forms of offense very well and one thing that is quite well countered by a defense meant to stop run plays and short passes is medium passes.

The most open down is 2nd and short followed by 1st and 10. On 2nd and short the defense has to choose between trying to stop the run for a 1st down or the big pass play, this means as an offense you can try to guess which they are going for and counter it, but it will always be a guess - some times they may go cover 3 with underneath zones and your screen play is going to come up lame in that situation, on the other hand your delayed handoff with a pulling offensive lineman may gain a ton of yards - on the same down they could go run blitz with man on the outside in which case your screen may work like a charm but your delayed handoff gets stuffed in the backfield. You can play the odds of course by what a defense has done previously in similar situations, but really it is like switching your pitcher depending on what side of the plate a batter swings from, it only buys you a few %.

I work for a campaign management firm right now, and do a little investment banking on the side, so I use quite a bit of stats. I'm getting my Masters in finance, and taking my first calculus class ever this quarter (the previous exchange derivative models I've used either had the calc already done, or it was a simple click in excel). The calc class is going to kill my GPA, but my engineer dad might help me out.

I'm about to look for something along the lines of assistant DB/WR coach for a HS around here, and I want to see if some of my methods apply to the football field. I would love to coach a football team on a staff with you on it.

Boomhauer

12-03-2011, 04:58 PM

Any math whizzes on here?

OP- "I've always thought that if someone could formulate a statistical model for winning based on numbers..."

A) People that are good at math take calculus. People that aren't take statistics after flunking algebra.

B) People that know sports analyze players/systems. People that don't rely on stats for a whiff.

Willynowei

12-03-2011, 05:49 PM

Any math whizzes on here?

OP- "I've always thought that if someone could formulate a statistical model for winning based on numbers..."

A) People that are good at math take calculus. People that aren't take statistics after flunking algebra.

B) People that know sports analyze players/systems. People that don't rely on stats for a whiff.

Some people who are good at math take Statistics because jobs in finance at one point at least, paid quite a bit better than jobs in Engineering.

Archer81

12-03-2011, 06:23 PM

I'm taking statistics. Not because I flunked Algebra...I simply hate math, and the faster I can get my math credit the sooner I will never have to think about math ever again.

:Broncos:

That One Guy

12-03-2011, 06:27 PM

I'm taking statistics. Not because I flunked Algebra...I simply hate math, and the faster I can get my math credit the sooner I will never have to think about math ever again.

:Broncos:

When I see comments like this, I want to punch myself in the scrotum for my degree choice.

I've had to take algebra and am taking my calc final tomorrow and those are, by far, some of the easier classes I've taken. Things like genetics and organic chemistry make me yearn for the days when my classes centered around mathematical laws and theorems. I think I chose the wrong career path...

That One Guy

12-03-2011, 06:30 PM

By the way, I saw this just the other day and thought it was really interesting. The guy surely has his systems but there's clearly other things involved (the 'human element') that you have to consider that a computer may never be capable of doing.

<iframe width="560" height="315" src="http://www.youtube.com/embed/limVVER9X1I" frameborder="0" allowfullscreen></iframe>

Archer81

12-03-2011, 06:33 PM

When I see comments like this, I want to punch myself in the scrotum for my degree choice.

I've had to take algebra and am taking my calc final tomorrow and those are, by far, some of the easier classes I've taken. Things like genetics and organic chemistry make me yearn for the days when my classes centered around mathematical laws and theorems. I think I chose the wrong career path...

I've never been good at math, so subsquently I have never liked it. Everything else I can breeze through and I get the concepts quickly. I have to take my time with math and I hate that. In HS I doubled up when I could so I would not have to deal with algrbra or calc or anything else my senior year. And then I went to college, and the stupid ass state of Colorado has stupid ass math as a stupid ass required credit.

:Broncos:

mwill07

12-03-2011, 09:06 PM

Some people who are good at math take Statistics because jobs in finance at one point at least, paid quite a bit better than jobs in Engineering.

Working engineers should find statistics much more useful than calculus. It's unfortunate, IMO, that most engineers don't have a very good stats background.

It's also true that finance pays better than engineering.

Mogulseeker

12-03-2011, 10:44 PM

Some people who are good at math take Statistics because jobs in finance at one point at least, paid quite a bit better than jobs in Engineering.

Only if you're good at finance. The income gap between poor and extremely wealthy is very wide in the financial field.

Broncbow

12-04-2011, 02:44 AM

Don't let the numbers fool you on Tebow

Tebow isn’t like any of his predecessors. He isn’t a “scrambler.” He’s a downhill runner — easily as big as most fullbacks — who runs from the pocket, typically charging into an already spread-out field.

How do you measure that? Being a mere hyperbolist, I called someone who understands these metrics. Sean Lahman is a reporter specializing in databases, and author of The Pro Football Historical Abstract. In his attempt to make Bill James-ian sense of the NFL, Lahman came up with a theory of “Adjusted Yards.” It’s a particularly useful tool when applied to quarterbacks, as it reflects fumbles, sacks, interceptions and rushing yards in addition to the usual passing numbers...

In Tebow’s case, the conventional numbers lie. His quarterback rating of 80.5 would rank him 21st in the league. By Lahman’s measure of "Adjusted Yards," however, he’s no worse than ninth.

Still, because the nine games in which Tebow has appeared (six as a starter, three in relief) are an admittedly small sample, Lahman came up with a better way to gauge Tebow’s effectiveness. It’s a spread sheet that ranks quarterbacks by "Adjusted Yards per Touch" (“a touch” being defined as pass and rushing attempts plus sacks). By that measure, Tebow gains an average of 2.61 yards every time he touches the ball. Maybe that doesn’t sound like much, but only four quarterbacks have doe better this season. In order, they are Rodgers, Drew Brees, Brady and injured Matt Schaub. Tebow is No. 5.

If that’s pretty damn good, don’t be so surprised. It’s only what you should expect from a quarterback who’s 5-1 as a starter.

Lahman’s numbers don’t lie. They’re more complete than the quarterback ratings. They’re not intuitively flawed like the eyeball test. (“You see him? I threw better than Tebow in junior high.”) And they don’t depend on my specialties, to wit: hyperbole and sentiment.

After six starts, it’s not yet clear what Tebow represents: an anomaly or, perhaps, a new figure in the evolution of sports’ most interesting position...

http://xfinity.comcast.net/articles/sports-nfl/20111202/Kriegel-Tim-Tebow-Denver-Broncos-NFL/

That One Guy

12-04-2011, 08:28 AM

Only if you're good at finance. The income gap between poor and extremely wealthy is very wide in the financial field.

I'd say the income gap between the extremely wealthy and the poor is wide in any field.

Our company does this daily on other market oriented studies and spends millions each year backtesting coefficients...trust me when I say...there will always be outliers anomalies to the model that really make the model more of a probability and speculation tool than an firm investment by which you can guarantee a certain result. I can tell you who is most likely to spend and on what and when but whether that actually happens or not is speculation.

Sorry, I don't believe you.

Old Dude

12-04-2011, 09:57 AM

I like the math on this site:

http://www.coldhardfootballfacts.com/Articles/11_4846_Broncos_Crusade_into_Twin_Cities:_5_Things _to_Expect.html

Broncbow

12-05-2011, 06:29 AM

[SIZE="5"]Still, because the nine games in which Tebow has appeared (six as a starter, three in relief) are an admittedly small sample, Lahman came up with a better way to gauge Tebow’s effectiveness. It’s a spread sheet that ranks quarterbacks by "Adjusted Yards per Touch" (“a touch” being defined as pass and rushing attempts plus sacks). By that measure, Tebow gains an average of 2.61 yards every time he touches the ball. Maybe that doesn’t sound like much, but only four quarterbacks have doe better this season. In order, they are Rodgers, Drew Brees, Brady and injured Matt Schaub. Tebow is No. 5.

If that’s pretty damn good, don’t be so surprised. It’s only what you should expect from a quarterback who’s 5-1 as a starter.

6-1 as a starter~!!8')

Old Dude

12-05-2011, 06:36 AM

Tebow's World:

http://www.coldhardfootballfacts.com/Articles/11_4861_It%27s_Tebow%27s_world%2C_we%27re_just_liv ing_in_it.html

Mogulseeker

12-05-2011, 08:54 AM

I'd say the income gap between the extremely wealthy and the poor is wide in any field.

If we're talking between CEO and average worker, maybe... but the vast majority of Americans are living between the mean income for the state.

In finance, it's entirely possible to make billions in a year or, more likely, actually be in the negatives for the year.

My dad (an engineer) wasn't making too much money in finance until his stocks split in 2006 and he made $2 million. He's been in the negatives ever since then.

Boomhauer

12-05-2011, 05:12 PM

mwill07 - "Working engineers should find statistics much more useful than calculus..."

a) Engineers don't use guessing and probability to design something. The probability of certain wind velocities, automotive traffic or combustion instability can define the tolerances required, but then sound sciences and mathematics (calculus) is used during the actual engineering.

b) Statistics has some uses - stocks, gambling, agriculture, sales - but no use when a definite answer is required. It's also useless in small scale and being spot-on is an anomaly. Overall, stats/probability is used to try and get a 'feel' for something, not to get answers, so is popular among 'analysts' that are payed for words, not accuracy.

To get back to the OP and his question about statistical models in sports;

a) 'Any given Sunday' is another way of saying the human element and chaotic nature of sports makes predicting a game or individual performances futile. Only the vast number of games and performances Vegas does probability on, and span/number of investments analytical traders do, have the scale to show results.

b) If you need an example; Watch a game with Madden, then watch it that week.

mwill07

12-05-2011, 06:12 PM

mwill07 - "Working engineers should find statistics much more useful than calculus..."

a) Engineers don't use guessing and probability to design something. The probability of certain wind velocities, automotive traffic or combustion instability can define the tolerances required, but then sound sciences and mathematics (calculus) is used during the actual engineering.

b) Statistics has some uses - stocks, gambling, agriculture, sales - but no use when a definite answer is required. It's also useless in small scale and being spot-on is an anomaly. Overall, stats/probability is used to try and get a 'feel' for something, not to get answers, so is popular among 'analysts' that are payed for words, not accuracy.

couldn't disagree more. engineers use guessing and probability to design all the time. Pure numbers just don't exist - every number has an associated variation.

Calculus, on the other hand, has almost always been resolved to useful equations by the time an engineer wants to design a widget. There is some theoretical stuff being done, but that's mostly on the academic side. That's what I meant by "working engineers".

personally, I've done a hell of a lot more tolerance analysis than calculus. I don't think I've done a single integration or derivative since grad school.

Boomhauer

12-05-2011, 06:42 PM

a) mwill07 "...engineers use guessing and probability to design all the time"

Re- I can't imagine what work you do that doesn't require any accuracy, except maybe Chinese toys or CO schoolhouses.

b) mwill07 "...I've done a hell of a lot more tolerance analysis than calculus."

Re- Than your 'analysis' wasn't worth the paper it was written on, or to repeat, ...'analysts' are payed for words, not accuracy.

c) Don't know who you are or what you do, but pray I never have the misfortune of working with you or relying on your work.

mwill07

12-05-2011, 07:11 PM

^^^I can't imagine what work you do that doesn't require any accuracy, except maybe Chinese toys.

close...mass produced consumer goods, manufactured in China.

Here's thing though - for anything manufactured at a high volume, there will be natural variation. If the design is even a little bit aggressive, you have to be cognizant of that variation. I had a whole thing typed up as to why, but googled it and found a better explanation here. (http://www.pdnotebook.com/2010/06/statistical-tolerance-analysis-root-sum-square/) You can read up on it if you like, it gets a bit nerdy, but that's essentially what I do.

Mogulseeker

12-05-2011, 07:14 PM

couldn't disagree more. engineers use guessing and probability to design all the time. Pure numbers just don't exist - every number has an associated variation.

Calculus, on the other hand, has almost always been resolved to useful equations by the time an engineer wants to design a widget. There is some theoretical stuff being done, but that's mostly on the academic side. That's what I meant by "working engineers".

personally, I've done a hell of a lot more tolerance analysis than calculus. I don't think I've done a single integration or derivative since grad school.

hmmm...

Uhhh. If I'm working in a office tower, I hope the engineers who designed it didn't "guess" on how much weight it can probably hold.

mwill07

12-05-2011, 07:24 PM

hmmm...

Uhhh. If I'm working in a office tower, I hope the engineers who designed it didn't "guess" on how much weight it can probably hold.

do you think they know exactly how many people will be on a given floor at a given time? do you think they know exactly what the tensile stress of the girders is, to 8 significant digits?

In real life, we do not have exact numbers for anything. We make assumptions. We bound those assumptions to be conservative, and apply a generous factor of safety. We test those assumptions, and re-test them. We understand where the assumptions are valid, and we understand where they are not.

Mogulseeker

12-05-2011, 07:42 PM

do you think they know exactly how many people will be on a given floor at a given time? do you think they know exactly what the tensile stress of the girders is, to 8 significant digits?

In real life, we do not have exact numbers for anything. We make assumptions. We bound those assumptions to be conservative, and apply a generous factor of safety. We test those assumptions, and re-test them. We understand where the assumptions are valid, and we understand where they are not.

I'm an economist, not an engineer, but I always do my numbers to three or four digits, and what I'm seeing here is.... you're telling me that if everybody in the building somehow decided to go to the top floor, there can be no guarantee that the building wont collapse?

mwill07

12-05-2011, 07:48 PM

I'm an economist, not an engineer, but I always do my numbers to three or four digits, and what I'm seeing here is.... you're telling me that if everybody in the building somehow decided to go to the top floor, there can be no guarantee that the building wont collapse?

lol...no. I don't know what the standard factor of safety is in the construction industry, but i'm sure it's north of 2.0...that is, designed to be at least 2x as strong as the biggest, conceivable load.

now, if everyone was on the top floor and jumped at the same time...

broncosteven

12-05-2011, 08:39 PM

I've never been good at math, so subsquently I have never liked it. Everything else I can breeze through and I get the concepts quickly. I have to take my time with math and I hate that. In HS I doubled up when I could so I would not have to deal with algrbra or calc or anything else my senior year. And then I went to college, and the stupid ass state of Colorado has stupid ass math as a stupid ass required credit.

:Broncos:

I am guessing that is when you fell in love with ass? or did you get sucked into it?

LOL