[Rudbaeck]

Or you could just add the numbers to the following formula and plug away.

You can be 95% certain that your true win rate is within 1.98*SD/sqrt(n) where n is the sample size. As SD is measured in BB/100 n is one group of 100 hands. Say for example you have played 40000 hands then n = 400.

1.98 is used merely because we know that 95% of all results are within 1.98 standard deviations from the mean.

So let's say we have won 2.5BB/100 over 50k hands and have a standard deviation of 16BB/100. Smashing stats for a limit player.

Then we can be 95% certain that his true result is within 1.98*16/sqrt(500)=1.41... So we can with 95% certainty say that his long term true win rate is between 1.1BB/100 and 3.9BB/100.