|
asdpikas
|
03-14-2009, 10:41 AM
Post subject: Interpreting standard deviation?
|
#1 (permalink)
|
|
Full House
Join Date: Jul 2007
Posts: 1,056
|
|
anyone used to this stat?
Just upgraded PT3 and this stat is now available. I've never used it before. What is normal? what is very swingy? how do i interpret any nr? say, 35.6 SD (BB/100) at 3/6 6max
|
|
|
Play for FREE and practice your game at...
Join the FTR Poker Forum to disable these banners and start posting!
|
|
DrivingDog
|
|
Full House
Join Date: Jul 2007
Location: UK
Posts: 923
|
|
It's a measure of how much something varies. The higher it is, the less consistent the data.
35 is very high for 6 max. About half of that is normal. I suspect your sample size is quite small.
|
|
"You can fool some of the people all of the time, and those are the ones you want to concentrate on." (George Bush).
|
|
asdpikas
|
|
Full House
Join Date: Jul 2007
Posts: 1,056
|
|
what's a good sample size? my std for 1/2 6max is 41.24BB/100 over 80k hands. For 2/4 6max it's 48.83BB/100 over 93k. The 3/6 above is only over 30k.
|
|
"could I take out every woman and child in a border town?"
For the right to be governed, waste them without mercy.
When you've decided. Meet me at the airport.
|
|
BennyLaRue
|
|
Full House
Join Date: Sep 2007
Posts: 646
|
|
Those are crazy high StDevs. As Dog said, 15 to 20 is probably a more normal range. The smaller your StDev is (given a significant sample, which 80k is), the more confident you can be that your true performance is as your stats suggest.
That said, looking at it in isolation won't tell you much. Dog wrote a good post once on the practical application of StDev.
http://www.flopturnriver.com/phpBB2/...68.html#649164
|
|
|
|
asdpikas
|
|
Full House
Join Date: Jul 2007
Posts: 1,056
|
|
wow.... +- 2.85 BB/100 at 1/2 with a CI of 95%
i guess at least i'm 95% sure i'm a winning player at that level. Whether my true winrate is 0.6 or 6.2.... i'll never know.
Is StD related to style? My very aggressive style favors big swings compared to nittier players. Bigger variance. Does this matter?
|
|
"could I take out every woman and child in a border town?"
For the right to be governed, waste them without mercy.
When you've decided. Meet me at the airport.
|
|
DrivingDog
|
|
Full House
Join Date: Jul 2007
Location: UK
Posts: 923
|
|
SD is using samples of 100 hands, so 30k hands provides 300 such samples (30000/100 = 300). That's plenty.
Your style definitely influences your SD. More aggressive players win and lose bigger pots, which means they have higher SD.
|
|
"You can fool some of the people all of the time, and those are the ones you want to concentrate on." (George Bush).
|
|
BennyLaRue
|
|
Full House
Join Date: Sep 2007
Posts: 646
|
|
Bumpage. Given your hudge sample now, asd, what's your SD like?
|
|
|
|
asdpikas
|
|
Full House
Join Date: Jul 2007
Posts: 1,056
|
|
Quote:
|
Originally Posted by BennyLaRue
Bumpage. Given your hudge sample now, asd, what's your SD like?
|
Overall, 17.09 BB/100, says PT3
|
|
"could I take out every woman and child in a border town?"
For the right to be governed, waste them without mercy.
When you've decided. Meet me at the airport.
|
English
Deutsch
Español
Français
Italiano
Nederlands
Pусский
Svenska
05-26-2012, 03:08 PM Australia Legalized Online Poker coming up in next 6 to 12 Months
Linear Mode
