Variance

[DpR]

[ QUOTE ]


You cant just put % on one of the axes.

[/ QUOTE ]

I know, I didnt suggest only using it one axis.

[ QUOTE ]
Linear means that for each 1 unit increase in one axis, there is a fixed amount of increase or decrease on the other axis. (As an aside, this comparison should probably be win rate vs risk of ruin instead of win rate vs required bankroll). For this example, for the relationship to be linear the additional amount of bankroll required for a decrease in win rate from 2.0 to 1.5, for example, should be the equal to the additional amount of bankroll required for a decrease in win rate from 1.5 to 1.0. That isn't the case here.

[/ QUOTE ]

Well duh, no one should ever consider that to be what anyone is referring to if they said there was a linear relationship between WR and Bankroll required. Obviously, the scenario you describe for any poker scenario since the BR required will be infinity for all WR <0, thus it will be assymptotic as x->0. Percentage are clearly implied in this conversation (or use natural logs if u like).

The interesting question is, does variance increase with a decrease in WR.

[Abbaddabba]

The actual figure of STDV/100 is independent of your winrate.


The swings seem smaller when you have a higher winrate because they tend to gravitate towards a higher average.

If you're a 3BB/100 winner historically and run at 2BB/100, it's not going to be busting your balls like it would for a 0.5BB/100 winner to run at -0.5BB/100.

[DpR]

[ QUOTE ]
The actual figure of STDV/100 is independent of your winrate.



[/ QUOTE ]

What makes you so certain? ( I do not mean from a statistical perspective on a given sample)

[Abbaddabba]

Are you saying that you think there's a positive or negative relationship between the two figures?

[danzasmack]

I don't knnow schneids as well as PBob, but this post of his made this whole thread seem pretty crazy (double funny if I remember Dean's location correctly).

Though I still side with the "you can have a 1k BB downswing" camp. This post was more for humor.

[El Diablo]

aba: It is unlikely that you and cts made those leaps without being good players. However, other players just as good as the two of you did not make the same leaps as you because they did not run as good as you. It is important to note that saying "look at poker tracker, over that 750k hands, I bet I ran no more than x% better than expectation" or something like that does not really prove all that much. WHEN variance hits is critical. People who run a little better than average when they take shots or jump up levels have dramatically better results.

josh: "that I started to miss easy valuebets on the river, played to weak in general, missed checkraises, etc." Aha! That's exactly what I guessed was exacerbating the problem in that thread! Glad to hear you've identified/acknowledged that, hopefully that helps you prevent another slide from getting quite that bad.

bk: I challenge you to a 10/20 LHE HU match. Also, YOU OWE ME $100 PAY UP NOW MOFO.

[stinkypete]

[ QUOTE ]
"0.25....1941
0.5.....970"

what some excellent players are experiencing. TOUGH GAMES! have fun kids.

[/ QUOTE ]

these are "bankroll requirements" with a 5% risk of ruin. that's their chance of going busto without ever adding to or removing from their bankrolls. in other words, there's a 5% chance they'll have a downswing that big starting right now. over a long time period, they're almost certain to have a downswing that big.

does anyone know how to calculate the chances of having an x BB downswing over y hands based on winrate/sd? my statistics knowledge is a bit weak. if that's too difficult, has anyone run any monte carlo simulations for this kind of stuff? if not, i think i might do that sometime soon. it should be pretty straightforward. if anyone's less lazy than me and wants to code a simulation before i do, please send source code and results.

i feel like something like this was done a while ago, but it wasnt very extensive... if anyone knows where the threads are, link me.

[bicyclekick]

[ QUOTE ]

bk: I challenge you to a 10/20 LHE HU match. Also, YOU OWE ME $100 PAY UP NOW MOFO.

[/ QUOTE ]

uhh, I paid you like a week ago, go check your pstars history again before SLANDERING me!!! :P

10/20 hu aye? THAT'S LIKE MY NORMAL STAKES I'M BUSTO REMEMBER? [img]/images/graemlins/tongue.gif[/img] ok ok fine deal.

Since going back to limit about a week ago: (playing only 2-4 tables which works a lot better and may have been a solid PART of why my downswing was so nasty)



That's 366 bets to the upward this year. I wonder where my downswing is now.

[Hobbs.]

pete,

I think this has what you're looking for (although server is down so I can't actually check)

http://archiveserver.twoplustwo.com/show...ost682045683150

[Micturition Man]

Hmm. Aba, not to be an anti-fanboy, but you really don't think you've been running well at PLO in the last few months?

It's not like I've been taking notes but I have seen you go what seems like 8 for 10 or so in 100k+ pots where you were coinflippish.

The previous poster overstated the case somewhat with the comment about 15-20 coinflip pots going the other way, but that kind of swing is hardly necessary to make a big dent in your results.

I have no idea what kind of downswings you've had in PLO but given that you play in some tough games they should be very large. Those +100 to +300k days should be interspersed with lots of -100k and -200k and some -400k sessions. And eventually you're going to have a -1M streak.

When that happens will it be because you suddenly started playing badly?