Any books that help teach how to make a model?

[mcduggly]

I was jut wondering if there are any books out there on the market that help with the math portion of betting, as well as walking you through how to do it. Any help would be appreciated.

[Dark Horse]

Sharp Sports Betting, Weighing the Odds in Sports Betting, and Conquering Risk.

[mcduggly]

I've read those but they don't really tell you where to start or how to do it.

[MonkeyF0cker]

Try Statistics 101 and go from there.

[mcduggly]

Try Statistics 101 and go from there.

I've taken two stats classes at Ohio State, but I have no idea where to go from there.

[MonkeyF0cker]

Surely, Ohio State has a Statistics undergrad. Try looking at the courses and their content and do some research.

[mcduggly]

Surely, Ohio State has a Statistics undergrad. Try looking at the courses and their content and do some research.

I'm pretty knowledgeable about statistics, I just don't know how to apply them to predicting scores/spreads of games. I don't know how to implement pace or power rankings into an equation to find what I'm looking for.

[MonkeyF0cker]

I'm pretty knowledgeable about statistics, I just don't know how to apply them to predicting scores/spreads of games. I don't know how to implement pace or power rankings into an equation to find what I'm looking for.

Well, nobody's going to hold your hand. If you are knowledgeable and you're incapable of applying what you've learned to real world problems, you don't stand much of a chance anyway.

[mcduggly]

Well, nobody's going to hold your hand. If you are knowledgeable and you're incapable of applying what you've learned to real world problems, you don't stand much of a chance anyway.

Haha. Ok man.

[zorba74]

Try "Without a Tout" or "Baseball Hacks." I own the former but not the latter so I can only say that "Without a Tout" should help you get started.

Sorry I couldn't have been of more help but I don't run models myself. Good luck.

[Waterstpub87]

Look at Quant finance books. Pick up Hull's Futures and Options. Try to figure out how industry professionals price uncertainty, and you should be on the right track to figure out how to price it yourself.

[mcduggly]

Try "Without a Tout" or "Baseball Hacks." I own the former but not the latter so I can only say that "Without a Tout" should help you get started.

Sorry I couldn't have been of more help but I don't run models myself. Good luck.

Thanks man, I appreciate it.

[buby74]

For football power ratings try http://www.amazon.com/Whos-The-Scien.../dp/0691154228 which goes through several common power rating systems. Also look at ken Massey's football ranking comparison site which compares about 100 systems for ranking and rating football teams. These systems have various amounts of detail (from zero to formulas) but will give you an idea of the issues involved and the different ways of approaching it. Also http://www.thepredictiontracker.com/ also has links to different power rating systems.

[mcduggly]

For football power ratings try http://www.amazon.com/Whos-The-Scien.../dp/0691154228 which goes through several common power rating systems. Also look at ken Massey's football ranking comparison site which compares about 100 systems for ranking and rating football teams. These systems have various amounts of detail (from zero to formulas) but will give you an idea of the issues involved and the different ways of approaching it. Also http://www.thepredictiontracker.com/ also has links to different power rating systems.

Thanks a lot, Buby, I appreciate the help man.

[FreeFall]

it sounds like you're being lazy if you have the knowledge.

Here is a simple model. Take the teams current win lose percentage and then rank them. The team with the higher one will beat the team with the lower one.

What is wrong with this model? What is right with it? Can you prove it?

Build on that if you seriously needed an idea of somewhere to start.

[mcduggly]

it sounds like you're being lazy if you have the knowledge.

Here is a simple model. Take the teams current win lose percentage and then rank them. The team with the higher one will beat the team with the lower one.

What is wrong with this model? What is right with it? Can you prove it?

Build on that if you seriously needed an idea of somewhere to start.

I have the knowledge of knowing what a Poission distribution is and what it represents, as well as other statistical concepts. I just don't know which information (offensive efficiency, defensice efficiency, plays per game, etc) to implement into the model and and how to backtest it. I feel like EVERY stat should matter, but I know some don't, so I'm confused as to which ones are needed. I guess that is the hard part though.

[LtDementia]

I have the knowledge of knowing what a Poission distribution is and what it represents, as well as other statistical concepts. I just don't know which information (offensive efficiency, defensice efficiency, plays per game, etc) to implement into the model and and how to backtest it. I feel like EVERY stat should matter, but I know some don't, so I'm confused as to which ones are needed. I guess that is the hard part though.

Here's a site that looks at various stats and their importance - plus some interesting discussions:

http://www.advancednflstats.com/

LT

[mcduggly]

Here's a site that looks at various stats and their importance - plus some interesting discussions:

http://www.advancednflstats.com/

LT

Thanks buddy, I appreciate it.

[Inspirited]

i love advancednflstats

[sayhey69]

I have the knowledge of knowing what a Poission distribution is and what it represents, as well as other statistical concepts.

sounds like youre ready to crush nfl lines

[mcduggly]

sounds like youre ready to crush nfl lines

I was simply stating that I know the basics of stats 101, phaggot.

[VLR100]

You have to remember that all models are wrong (no model can account for every variable present in the reality of what you are modelling). However some models are useful. With sports you just need a model that's slightly better than the models of other market participants.

[sayhey69]

I was simply stating that I know the basics of stats 101, phaggot.

i was simply stating that this is not nearly enough knowledge to create a model to beat nfl lines. if your stats 101 was like mine then all you learned was hypothesis tests and confidence intervals not even linear regression. gl with that

[mcduggly]

i was simply stating that this is not nearly enough knowledge to create a model to beat nfl lines. if your stats 101 was like mine then all you learned was hypothesis tests and confidence intervals not even linear regression. gl with that

I know more than just stats 101. I have taken several stats classes at Ohio State. Just shut the fukk up, you have contributed nothing to this thread besides retardation.

[cyberbabble]

Free statistics data files. I don't know about accuracy.

http://www.repole.com/sun4cast/data.html

This guy develops a quarterback rating that he says is "better" than the current NFL method. Not about betting. He discusses what and why he included/excluded various statistics and how he used regression. Easy to read without heavy math/stat.

http://etd.ohiolink.edu/send-pdf.cgi/Gober%20Jon%20M.pdf?osu1242922731

[Miz]

look into the basics of predicting/forecasting things other than sports. Look into the various ways that is done. Come back to predicting sports about a year after that. Not being a smart ass, just sharing personal experience. My success improved greatly this way.

[sayhey69]

I know more than just stats 101. I have taken several stats classes at Ohio State. Just shut the fukk up, you have contributed nothing to this thread besides retardation.

congrats dude. then either apply what youve learned or drop out of school and get a job. if you cant apply what you learn in class then college is a big waste of time and money. there i contributed actual advice.

[PatrickBateman]

Another shining example of someone asking for a litle bit of help and all the "geniuses" on this website crushing that person for not reason. Why bash when someone is just lookng for a little help? Get a life people. Help or just don't write anything. We get it your all millionaire playboy geniuses and the rest of us are scum on the bottom of your shoe. But for some reaosn you seem to pay alot of attention to that scum...Hmmmm, guess your not doing as well as you think, now are you?

[FreeFall]

It's more of people not wanting to help someone who has given nothing.

He came in here asking for help and not putting in any effort. If he came in saying this is what I found am I right then we have somewhere to go.

It's like me asking you where the buried treasure is and then getting mad when you don't give me a piece of the map.

You probably will get trolled more heavily in here though as there are some smart people that come through and don't take shit for an answer. So if you want to find more accurate truths than players talk you gotta be able to take the heat.

[339955]

op, go ahead and start making a model. as you come across problems search forum archives with those specific key words and ask more specific questions as they arise. just go ahead and start off working. then ask more specific questions as they arise.

[PatrickBateman]

Freefall,

I totally agree with you that if somone is going to come here asking for handouts, that person is sort of lame. I just don't agree that there should be a need to belittle these people. Some I believe are just nieve and looking for some help. Most are greenhorns with no direction. Just no reason to bash these same people. It's lame and also ant-productive, just as you pointed out about those coming in here looking for handouts.

In summation: Help out or just move along. No need to put people down. If they are looking for a handout and you don't want to help them, THEN JUST DON"T SAY ANYTHING.

We are here to be helped and help others, not be a-holes that are frustrated with their lives and feel the need to take it out on others.

BOL to everyone.

[sayhey69]

i gave the best advice in this thread

[Juret]

op, go ahead and start making a model. as you come across problems search forum archives with those specific key words and ask more specific questions as they arise. just go ahead and start off working. then ask more specific questions as they arise.

highly recommended

[Inkwell77]

look into the basics of predicting/forecasting things other than sports. Look into the various ways that is done. Come back to predicting sports about a year after that. Not being a smart ass, just sharing personal experience. My success improved greatly this way.

this is a sharp post

[big0mar]

Another shining example of someone asking for a litle bit of help and all the "geniuses" on this website crushing that person for not reason. Why bash when someone is just lookng for a little help? Get a life people. Help or just don't write anything. We get it your all millionaire playboy geniuses and the rest of us are scum on the bottom of your shoe. But for some reaosn you seem to pay alot of attention to that scum...Hmmmm, guess your not doing as well as you think, now are you?

Here is a thought: the guy looking for a little help is trying to take money out of the pockets of everyone he is asking. It is illogical for anyone that seriously participates in these markets to share any information.