Standard Deviation of PT Stats (Light Math)

[jrz1972]

[ QUOTE ]
Basically, you can be about 99% confident that your "true" winrate is within 3 standard deviations on either side of your current average winrate after 13K hands. I believe the confidence interval for just one SD is about 78% or so.

[/ QUOTE ]

You're getting "standard deviation" confused with "standard error."

Chris had a thread a while back describing how to go from SD to SE and how to estimate the confidence interval of your winrate.

[chris_a]

[ QUOTE ]
They basically mean that variance sucks ass.

[/ QUOTE ]

This standard deviation isn't terrible at all for this win rate.

[ QUOTE ]
The longer version basically says that every hundred hands you play, you're on average, 15.6327 BBs from what you would expect to win.

[/ QUOTE ]

Yeah that's the intuitive feel though it's not exactly right mathematically.

After 100 hands, you have won some amount X. You were expected to win 3.5 BBs or whatever. But you won X.

Variance = expected value of (X-3.5)^2
Std. Dev. is square root of variance.

Sorry to be pedantic.

[UncleSalty]

Gotcha, thanks.