
BGonline.org Forums
Variance reduction is unbiased but may be skewed
Posted By: Maik Stiebler
Date: Saturday, 11 April 2015, at 7:31 a.m.
In Response To: Variance reduction is unbiased but may be skewed (Timothy Chow)
If the luck is skewed, it doesn't follow that the luckadjusted aka variancedreduced result is.
In the ideal case, the variancereduced result of a single rollout trial is just the real rollout equity, thus the distribution of total luck must simply be the distribution of raw results with a sign change and shifted. The total luck inherits the skew of the raw results.
As deviation from the ideal case, noise is added to the variancereduced result on every roll due to imperfect evaluations. I can't say how the imperfections of evaluations are skewed.

BGonline.org Forums is maintained by Stick with WebBBS 5.12.