Steve Norden wrote:
>For the player who played 2900 original hands of QQ without a dealt quad. Let's say that before he played those hands he estimated a 99.9% chance that the game is honest and a 0.1% chance that he is being cheated. If the game is honest he would go 2900 hands without a dealt quad about once in 1100. Without going into deep math Bayes Theorem would say that the chance that the game is honest after going 2900 hands without a dealt quad=((1/1100)/((1/1100)+(1/1000)))=10/21=47.6%. - WOW!
But, besides the .1% being a blind guess which could be off by many
factors of ten, that's being completely selective in choosing the
criterion. To use Bayes Theorem, first establish the criterion, then
record results, then analyze them.
Posted by: 007 <007@embarqmail.com>
| Reply via web post | • | Reply to sender | • | Reply to group | • | Start a New Topic | • | Messages in this topic (20) |
