|
BGonline.org Forums
Quartiles/Timothy
Posted By: Timothy Chow In Response To: Quartiles/Timothy (Fabrice Liardet)
Date: Thursday, 12 January 2012, at 6:05 p.m.
The first model that comes to mind is a Poisson distribution. But this is very crude. Roughly speaking, it says that the probability that you drop 0.010 units of equity now is independent of how long it has been since you last dropped 0.010 points. Backgammon errors are probably "clumpier" than that. For example, if you commit a whopper, then you drop ten times 0.010 units of equity all at once. Still, a Poisson distribution is the first thing I'd try.
|
BGonline.org Forums is maintained by Stick with WebBBS 5.12.