home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!europa.asd.contel.com!emory!swrinde!elroy.jpl.nasa.gov!nntp-server.caltech.edu!tylerh
- From: tylerh@cco.caltech.edu (Tyler R. Holcomb)
- Newsgroups: rec.gambling
- Subject: Re: Rabinowitz Sub-Sampling Roulette
- Date: 22 Nov 1992 19:59:29 GMT
- Organization: California Institute of Technology, Pasadena
- Lines: 40
- Message-ID: <1eoor1INN5el@gap.caltech.edu>
- References: <c5cNuB1w165w@student.business.uwo.ca>
- NNTP-Posting-Host: punisher.caltech.edu
-
- s4lawren@student.business.uwo.ca (Stephen Lawrence) writes:
-
- >Just got back from a 36 hour session in Las Vegas using the Rabinowitz
- >Sampling method, here are my results:
-
- >Day 1 (Thursday Nov. 19) Riviera Day 2 (Fri) Ballys Day 3 (Sat) Riviera
- >Hour 1 -$155 +$75 -$205
- >Hour 2 +$45 +$24 -$110
- >Hour 3 +$115 +$65 +$175
- >Hour 4 +$226 -$134 +$224
- >Hour 5 -$15 +$124 -$24
-
- >Total +$216 +$154 +$60
- >Total all three sessions +$430.00
-
- >Return on opening bankroll of $500.00 = $430/$500 = +86%
-
- Since the proper mathematicians in this group are probably
- tired of debunking posts like this, I think a lurking lightweigt
- like me will have to do.
-
- 1. Are these results are statistically significant? Roulette
- is a high- variance game (hence its popularity), so your sampling
- seems *way* too small to me.
-
- 2. Based on your empirical results, have you computed the probability
- of ruin? Any "sytem" where you regularly lose over 20% of your
- bankroll in an hour (e.g. saturday morning) strikes me a pretty
- good way to go broke.
-
- 3. Until I see a more mathematical treatment of your data, I will
- place greater credence in the "passenger 57" system: always bet
- black.
-
-
- --
- ---------------------------------------------------------------------------
- Tyler Holcomb * "Remember, one treats others with courtesy and repsect *
- tylerh@juliet * not because they are gentlemen or gentlewomen, but *
- caltech.edu * because you are." - paraphrased from Garth Henrichs *
-