Variance?

[Flying Dutchman]

False, you always talked about differences in assessing EV, the part that exists in both types of betting. Here you started talking about variances, the subject what has never been brought up in this way, and, unlike EV, addressing variance is neither common nor comparable issue. In fact, it is NOT an issue in sports betting due to fixed odds betting.



I got it, you are good, I am bad, your shit don't stink, I am not too good to even realize this.

It could be funny when an ignorant troll fails like in example a few messages above, it is rather sad when a good poster fails and starts talking exclusively about personalities and their stories.

Here are a few points on the subject matter which is variance and Kelly:
1) the OP question is clearly about sports betting, you bring up an issue irrelevant to sports betting
2) where variance is an issue (BJ, finance), any assumptions about variance are not within Kelly theory but rather are the shortcuts on the bettor's part, the bettor can use any approach to assessing variance while staying within Kelly framework
3) the issues with variance (where exist) are not an argument against using Kelly because the errors caused by mistakes in assessing variance are of much lesser significance comparing to the errors caused by mistakes in assessing the means.

Look, he told you how he did it, and he told you he's done with the subject. And you keep yapping about it in typical TROLL fashion.

You want to show some proof of what you say or not?

Or are you going to handle it like your Troll butt-buddy MF and say it can be done if you worked at it long enough?

[Flying Dutchman]

Whoops, I'm mixing up Monkey-wacker and "Data"

My oh my, how ever did that happen?

Are you guys running in a wolf...er...trollpack or something? You all show up at the same time and sound the same, I can't tell you apart.

[Data]

Any benefit in attempting to smooth out variance by playing favorites on the ml and taking the points with dogs? If a play is +ev then generally it'll be +ev money line and spread... is it best to simply choose the play that gives the largest +ev or should you look to lower variance if possible?

No, it is not wise "to simply choose the play that gives the largest +ev". You want find an equilibrium of sorts that accounts for both, ev and variance. One of the more popular (perhaps, the most reasonable) solution for this is to maximize the expected growth of your bankroll and that is when you use a staking scheme based on Kelly Criterion. The question you asked has already been discussed, the short answer is, to lower your variance, do not give up +EV but rather lower you bet size:

http://forum.sbrforum.com/handicapper-think-tank/134484-fav-minus-points-fav-ml-blend-plays-worthwhile.html

[Data]

Simply bankroll variance.

Good, you had me worried with scoring distributions reference.

It would involve changing your multiplier to fit a specific volatility threshold.

QFT. Finally, we have the right answer to OP's question.

It would certainly not be optimal, but would ensure that you were not overstaking. It's a very poor idea. However, it could be done.

I think it is a wonderful idea (to bet Kelly multiplier that is less than 1) and this is why it is so widely used. What it does it fits Kelly to bettor's risk preferences. I just cannot see a connection with scoring distributions.

[roasthawg]

No, it is not wise "to simply choose the play that gives the largest +ev". You want find an equilibrium of sorts that accounts for both, ev and variance. One of the more popular (perhaps, the most reasonable) solution for this is to maximize the expected growth of your bankroll and that is when you use a staking scheme based on Kelly Criterion. The question you asked has already been discussed, the short answer is, to lower your variance, do not give up +EV but rather lower you bet size:
http://forum.sbrforum.com/handicappe...orthwhile.html

Yeah, lowering Kelly isn't what I'm after as that's lowering eg as well. I was looking for a way to lower variance WITHOUT lowering eg... which I thought might be possible if +ev bets on favorites presented roughly the same value on both ml and spread. All my stuff is done with spreads and I have no easy way of comparing ml's to spreads without spending a bunch of time on it. So in the hopes of getting an accurate answer without spending a ton of time on it I'm gathering that for the most part the expected value on a spread bet is not equivalent to the ev on ml bet meaning that you'd have to sacrifice eg for variance which is not ideal.

[MonkeyF0cker]

OK I'm game, where's your citation? Kelly wrote more?

Show a poor dumb-shit like me your golden equation that mods Kelly for variance, dweeb. Remember, we need proof that is it optimal or you go into the locker again.

I would suggest that you read this paper since you don't even know that the Kelly formulas for Blackjack and sports are not indistinguishable.

http://www.bjmath.com/bjmath/thorp/paper.htm

Hopefully, you can read since apparently you couldn't comprehend my previous posts stating that reducing the Kelly multiplier to reduce variance WOULD NOT be optimal.

[MonkeyF0cker]

Yeah, lowering Kelly isn't what I'm after as that's lowering eg as well. I was looking for a way to lower variance WITHOUT lowering eg... which I thought might be possible if +ev bets on favorites presented roughly the same value on both ml and spread. All my stuff is done with spreads and I have no easy way of comparing ml's to spreads without spending a bunch of time on it. So in the hopes of getting an accurate answer without spending a ton of time on it I'm gathering that for the most part the expected value on a spread bet is not equivalent to the ev on ml bet meaning that you'd have to sacrifice eg for variance which is not ideal.

Precisely.

[MonkeyF0cker]

Good, you had me worried with scoring distributions reference.



QFT. Finally, we have the right answer to OP's question.



I think it is a wonderful idea (to bet Kelly multiplier that is less than 1) and this is why it is so widely used. What it does it fits Kelly to bettor's risk preferences. I just cannot see a connection with scoring distributions.

Sorry, Data. I didn't really intend to make that the only qualifier. Any method of quantifying your edge would be sufficient.

[Flying Dutchman]

I would suggest that you read this paper since you don't even know that the Kelly formulas for Blackjack and sports are not indistinguishable.

http://www.bjmath.com/bjmath/thorp/paper.htm

Hopefully, you can read since apparently you couldn't comprehend my previous posts stating that reducing the Kelly multiplier to reduce variance WOULD NOT be optimal.

Why...thanks, Monkey!

Hey everybody, something useful from Monkey for a change.

But I'm happy to see that your link did come with your typical condescending remark about my ability to read your crappy language that you Americans continue to mangle. Or, perhaps since you know it is my second language, you were indeed worried that I had misread your post...

...nah, your MO in all the forums is the vicious put-down. As any visitor to the zoo knows, monkeys always have to throw shit...

[bztips]

Pot...

Why...thanks, Monkey!

Hey everybody, something useful from Monkey for a change.



your MO in all the forums is the vicious put-down. As any visitor to the zoo knows, monkeys always have to throw shit...

Meet kettle...

90% of you Americans couldn't add up 10 3-digit numbers and get the same answer twice. And you call yourselves a "Technical Society." The Chinese, who can add, are busy eating your lunch since W has run off all the immigrants who were attending your universities, staying in the USA, and making you dumb schmucks rich by job creation mostly in the high tech area.

Get used to ramen noodles, America.

[Flying Dutchman]

Pot...

Meet kettle...

When these clowns go after some poster on an inane math point that they are short of knowledge on, or they just want to beat up because they are basically unhappy, insecure personalities I give them a taste of their own medicine.

I'm the Dexter of the Tank, I know I'm a monster; these sad-sack dweebs think they are "enlightened."

Now as to the education remark about you math-stupid Americans: deal with it. The Chinese are fricking Commies, for Pete's sake, running a mercantile society and out to dominate the world. You dumb-shits need to wake the fvk up and protect what was once the best and brightest society in the world.

Good advice, if you ask me.

[MonkeyF0cker]

When these clowns go after some poster on an inane math point that they are short of knowledge on, or they just want to beat up because they are basically unhappy, insecure personalities I give them a taste of their own medicine.

I'm the Dexter of the Tank, I know I'm a monster; these sad-sack dweebs think they are "enlightened."

It's quite clear whom the one short on knowledge is after reading this thread.

It's extremely ironic that you call us trolls, yet we were the only ones to actually help the OP. Meanwhile, Wrecktangle misinforms and misleads. And your only contributions to this thread are pathetic attempts at mudslinging. You really should quit trying to project yourself on others.

The two of you are probably the most useless posters in the Think Tank.

[Flying Dutchman]

It's quite clear whom the one short on knowledge is after reading this thread.

It's extremely ironic that you call us trolls, yet we were the only ones to actually help the OP. Meanwhile, Wrecktangle misinforms and misleads. And your only contributions to this thread are pathetic attempts at mudslinging. You really should quit trying to project yourself on others.

The two of you are probably the most useless posters in the Think Tank.

This from "The Angry Man." A term not only used in this forum but others as well.

You damn yourself by the shit you spew. When you attempt to tear down folks that many others see value in, you mearly reflect on yourself.

Karma's a bitch, dude.

[MonkeyF0cker]

This from "The Angry Man." A term not only used in this forum but others as well.

You damn yourself by the shit you spew. When you attempt to tear down folks that many others see value in, you mearly reflect on yourself.

Karma's a bitch, dude.

I damn myself? LOL. How? I think you've made enough of a fool of yourself already in this thread. Know when to quit.

[Flying Dutchman]

I damn myself? LOL. How? I think you've made enough of a fool of yourself already in this thread. Know when to quit.

Why should I quit? I certainly don't claim to be a smart asshole like you, attempting to lord my supposed knowledge over everyone. We just laugh at you. Your atomic-level "pitch-by-pitch" Monte Carlo Baseball simulation was classic modeling overkill by an ** rube. An excellent way to introduce error with additional modeling complexity by adding more distributions to manage.

You quoted one source, and I applauded you for probably the only time I've seen you contribute anything except bile and discontent (and we're seeing more of that now) and neither of you certainly never countered Wreck's point which was: for any particular situation, sports or otherwise, the variance on either side of the mean is about the same in any practical situation (i.e. win rate between 45-55%). Reducing the Kelly BR fraction for variance was never his point, it's Data's point that you continue to push just to get into an argument and throw shit, about the only reason you ever post anywhere.

As far as reducing Kelly for variance, yep, been there. Anyone who has built a betting simulator, has seen this. Tightening it down for the particular sport is the trick; been there too.

Comon, call me a dumb-shit again, I kinda like it...

[MonkeyF0cker]

Why should I quit? I certainly don't claim to be a smart asshole like you, attempting to lord my supposed knowledge over everyone. We just laugh at you. Your atomic-level "pitch-by-pitch" Monte Carlo Baseball simulation was classic modeling overkill by an ** rube. An excellent way to introduce error with additional modeling complexity by adding more distributions to manage.

You quoted one source, and I applauded you for probably the only time I've seen you contribute anything except bile and discontent (and we're seeing more of that now) and neither of you certainly never countered Wreck's point which was: for any particular situation, sports or otherwise, the variance on either side of the mean is about the same in any practical situation (i.e. win rate between 45-55%). Reducing the Kelly BR fraction for variance was never his point, it's Data's point that you continue to push just to get into an argument and throw shit, about the only reason you ever post anywhere.

As far as reducing Kelly for variance, yep, been there. Anyone who has built a betting simulator, has seen this. Tightening it down for the particular sport is the trick; been there too.

Comon, call me a dumb-shit again, I kinda like it...

LMAO. Your reading comprehension is atrocious. I quoted you a source because it takes 5 times to tell you that there are disparate Kelly formulas for BJ and sports. Wrecktangle's point was that Kelly "assumes essentially constan(t) variance." He goes about trying to qualify it with a distribution from blackjack (a disparate formula from sports mind you). I believe I was the one who said that the multiplier should be reduced rather than Data. Once again, you're the only one "throwing shit" in this thread. You did absolutely nothing aside from it. Although, your confusion over Kelly was highly entertaining. So, thank you.

By the way, good luck creating a profitable MLB model without a pitch-by-pitch database. It's pretty simple to effectively model a batter vs. pitcher scenario without knowing how a batter hits against the pitcher's pitch types. You're the expert though, dumb shit. LOL.

[benjy]

Damn, but this thread is entertaining.

[Flying Dutchman]

Damn, but this thread is entertaining.

You're welcome. Always try to be entertaining in some fashion, but when you have a supercilious shit-thrower like monkey-humper on the bar-be-que, it's really neat stuff.

This clown seems to really have no clue of what people think of him, and he thinks he can bully folks into paying some sort of twisted homage to him.

...so this is all about the Monkey, and it has been fun to see how big of an ass he makes of himself.

[MonkeyF0cker]

You're welcome. Always try to be entertaining in some fashion, but when you have a supercilious shit-thrower like monkey-humper on the bar-be-que, it's really neat stuff.

This clown seems to really have no clue of what people think of him, and he thinks he can bully folks into paying some sort of twisted homage to him.

...so this is all about the Monkey, and it has been fun to see how big of an ass he makes of himself.

Oh, yes. It's very difficult for me to realize that people don't like me. Almost as much as it is for you to realize that there are two different Kelly formulas for BJ and sports. The entertaining part is that you're trying to come across as intellectually superior in a thread that exposes you as not even knowing the difference in Kelly staking between BJ and sports. And again, you call me a shit stirrer when you didn't answer one of the OP's questions. You simply came in here to start shit. Quite ironic.