Select Page
Poker Forum
Over 1,291,000 Posts!
Poker ForumTournament Poker

Modelling SNG win rate with Binomial Distribution

Results 1 to 3 of 3
  1. #1

    Default .

    .
    Last edited by frjd2; 11-29-2011 at 07:45 AM.
  2. #2
    It seems like it might be possible to model using the binomial distribution if p tends towards 0, otherwise the shape is wrong Binomial distribution - Wikipedia, the free encyclopedia.

    Why do you want to model win rates?

    EDIT: Actually the binomial distribution is specifically for an experiment with only two outcomes. Try the Poisson distribution, which is also for discrete data.
    Last edited by Nakamura; 12-30-2011 at 12:59 AM.
  3. #3
    Poisson won't work here if you define multiple outcomes as 1st 2nd or 3rd. Either you want Binomial where success is defined as finishing ITM (shape is irrelevant) or Multinomial where the three events are 1st, 2nd, 3rd.

    Poisson will give you number of events within a given time frame and would only be remotely relevant if you were putting in long long sessions 24 tabling and wanted to look at the probability of getting X ITMs after the first hour.
    This is not my signature. I just write this at the bottom of every post.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •