Building a predictive model.

[Bread]

Alright, trying to get something more serious here... I want to come up with a model to pick winners. To make sure that I'm looking for the right things, I have some questions.

Lets take for example NBA over/under bets. I have a simple prediction model of the total score in the game (that doesn't work of course) and I want to tweak it to make it more accurate. In Minitab (statistical software) I run a "Descriptive Statistics" analysis, which tells me how far I am off, by looking at standard deviation. Here is what it told me:

Descriptive Statistics: diff

Variable N N* Mean SE Mean StDev Minimum Q1 Median Q3
diff 13194 0 -1.196 0.155 17.813 -113.469 -12.512 -0.759 10.891

Variable Maximum
diff 61.307

Standard deviation of 17.8. What is my goal here? Is it to bring down the standard deviation to a minimum? Would the model be more predictive if the standard deviation was, lets say, 4.6?

Also I checked how far off the actual over/under line. There isn't much of a difference:

Descriptive Statistics: diffBooks

Variable N N* Mean SE Mean StDev Minimum Q1 Median
diffBooks 13194 0 -0.411 0.151 17.292 -109.000 -11.500 0.000

Variable Q3 Maximum
diffBooks 11.500 69.000


Lines are way off too. Besides standard deviation, is there anything else I should look at? I have a very basic understanding of statistics, so I'm not sure what some of the numbers represent or what is of interest to me.


I also ran a regressional analysis on the same variables that are trying to predict the total score. Here is the result:

Regression Analysis: actualScore versus pvscore, phscore

The regression equation is
actualScore = - 8.15 + 1.06 pvscore + 1.03 phscore


Predictor Coef SE Coef T P
Constant -8.148 3.126 -2.61 0.009
pvscore 1.05628 0.03409 30.99 0.000
phscore 1.03302 0.03418 30.23 0.000


S = 17.7913 R-Sq = 23.8% R-Sq(adj) = 23.8%


Analysis of Variance

Source DF SS MS F P
Regression 2 1303249 651625 2058.64 0.000
Residual Error 13191 4175375 317
Total 13193 5478624


Source DF Seq SS
pvscore 1 1014079
phscore 1 289171

I have a question about the variable "R-Sq". The 23.8%, does that mean I only have 23.8% of all factors that make up an accurate predictive model? Do I need to search for the other 76.2%?


?

[durito]

i've read this post before

hi bread

[Bread]

hi!

[durito]

http://forum.sbrforum.com/handicapper-think-tank/65765-building-predictive-model-what-look.html

lol

[Bread]

Oh oh...you may have just uncovered one of my ghosts!

Damn you are good!

[durito]

I miss buddybear

[B1GER1C828]

[Bread]

Durito did you like the touch how I made the avatar a corpse (ghost)?

I was full of tricks back then.

[durito]

i turned avatars off

[Bread]

How rude!

[pavyracer]

Bread if your model is too complicated to be undestood by the average sports gambler it will be too troublesome to work. Forget about models. Keep track of a record for a month. Bet the games you like. If you can win by beating the vig at the end of the month then bet with real money. If you don't keep practicing until you get better. Models are a way for touts to say they are smart when in reality they have no clue on how to pick winners. My favorite cliche is this: "I am really sorry I lost 3 bets in a row but I was on the right side of the bet all 3 times so even though I lost I'm still sharp!"

[durito]

hi pavy

[Bread]

Bread if your model is too complicated to be undestood by the average sports gambler it will be too troublesome to work. Forget about models. Keep track of a record for a month. Bet the games you like. If you can win by bitting the vig at the end of the month then bet with real money. If you don't keep practicing until you get better. Models are a way for touts to say they are smart when in reality they have no clue on how to pick winners. My favorite cliche is this: "I am really sorry I lost 3 bets in a row but I was on the right side of the bet all 3 times so even though I lost I'm still sharp!"

Thanks for the info, Pavy. I might give this predictive model crap less consideration.

[Shark79]

U got toasted

[CarpeDime]

I despise people who understand all this sh*t




I have done some regression analysis on the Vancouver/Toronto game. Check this out:


VAR -><#34 * total goals - (.4x) +.862 DEV (nar std) %^*(.45)#<>^3

so,

STD DIFF .26 * -EV + POS RTSQ (.48)*^3

and if you fill in the linear data points you get:

P VAL = RT SQR ^ .5 AB<>X!!!


I have 96% confidence that I have a .03% edge on my bet

[Swinging Johnson]

Bread if your model is too complicated to be undestood by the average sports gambler it will be too troublesome to work. Forget about models. Keep track of a record for a month. Bet the games you like. If you can win by beating the vig at the end of the month then bet with real money. If you don't keep practicing until you get better. Models are a way for touts to say they are smart when in reality they have no clue on how to pick winners. My favorite cliche is this: "I am really sorry I lost 3 bets in a row but I was on the right side of the bet all 3 times so even though I lost I'm still sharp!"

Pavy...I believe you missed this Building a predictive model - what to look for? which was splendidly uncovered by durito above. Listen Bread, you just keep being the sexy bitch that you are and leave the statistical analysis for those less aesthetically blessed than you. You don't have to be a star baby to be in my (my my my) show.

[pavyracer]

Pavy...I believe you missed this Building a predictive model - what to look for? which was splendidly uncovered by durito above. Listen Bread, you just keep being the sexy bitch that you are and leave the statistical analysis for those less aesthetically blessed than you. You don't have to be a star baby to be in my (my my my) show.

OK. I didn't see this earlier. What is durito doing in the Players Talk? I thought that elitist snob was only good in his comfort zone.

[MrMonkey]

I miss buddybear

So does Taco!

[Bread]

I despise people who understand all this sh*t I have done some regression analysis on the Vancouver/Toronto game. Check this out: VAR -><#34 * total goals - (.4x) +.862 DEV (nar std) %^*(.45)#<>^3 so, STD DIFF .26 * -EV + POS RTSQ (.48)*^3 and if you fill in the linear data points you get: P VAL = RT SQR ^ .5 AB<>X!!! I have 96% confidence that I have a .03% edge on my bet

UPSURD!!

You state that

VAR -><#34 * total goals - (.4x) +.862 DEV (nar std) %^*(.45)#<>^3

When CLEARLY...

VAR -><#34 * total goals - (.4x) +.862 DEV (nar std) %^*(.45)#<>^3 if ( ( )==D

[MrMonkey]

You guys think Taco can't wait till Curious tour of with the Iraseli military is over?

[durito]

OK. I didn't see this earlier. What is durito doing in the Players Talk? I thought that elitist snob was only good in his comfort zone.

Hi pavy

[Richkas]

Models will get you 54% winners at best.