RE: [Bug-gnubg] Snowie 4 vs. GNU 0.13

[Ian Shaw]

> -----Original Message-----
> From: Øystein Johansen
> Sent: 09 June 2003 12:47
> To: Nardy Pillards; Joern Thyssen
> Cc: GnuBg Bug (E-mail)
> Subject: Re: [Bug-gnubg] Snowie 4 vs. GNU 0.13
> 
> 
> std.dev = sqrt( n * p * q )
> 
> p = Estimated probability of GNU winning based on the trials.
> q = 1 - p
> n = number of trials.
> 
> std.dev = sqrt( 100 * 0.56 * 0.44) = 4.964
> 
> -Øystein
> 
I did it the long way in Excel, making a column of 56 1s & 44 0s. I came up 
with 0.4964,  the same value as Øystein but for a power of 10. Excel's built in 
formula made it 0.4989. Are you sure you should have included n = 100 in there?

Being rather ignorant of stats, I also wondered if you should be scoring +1 and 
-1. This would give a mean of 0.12, in a ppg kind of way. The Std Dev is about 
0.99 if you do it this way. I suppose it's the difference between equity and 
winning chances.

--Ian