Re: Push more often=loss less often

Posted by Pete Moss on July 14, 1997 at 00:59:29: In Reply to: Re: Push more often=loss less often posted by David D'Aquin on July 13, 1997 at 22:26:23:

I agree with everything you said. I think somehow we are misunderstanding each other in a couple of these threads, because I don't see how what you said in any way contradicts what I said. There are two statistics we keep. One, which you guys call the EV, is the expected per-unit result -- the first moment of the random value R, the result of the hand. The other, which you call the VAR, is the expected squared per-unit result or second moment of R. We use those first two moments of R to approximate, with a two term expansion of the Taylor's series, the expected value of log(1+b*R), where b is the fraction of bankroll wagered. Both of those statistics must count the pushes as a hand played. If they didn't, you could change them dramatically by paying a miniscule amount instead of pushing -- say a trillionth of a cent.

Pete

---