Normalizing Errors

by Douglas Zare
1 July 2006

Douglas Zare

How do we measure the size of an error? How do we determine which errors are the most serious, and most worthy of attention? Two possibilities are to use match winning chances (mwc) and the money game equivalent (EMG). We'll see that neither is ideal, and that other normalizations are possible
 

GammonVillage Subscriptions:

Choose a subscription length. Your best value is the lifetime subscription.

Duration:

Price:

Expires:

3 Month Subscription

$30

03 Dec 2010

1 Year Subscription

$50

03 Sep 2011

Lifetime Subscription

$125

Never

Proceed to Step Two

Article text Copyright © 1999-2010 Douglas Zare and GammonVillage Inc.

Feedback about this article:

1.

Subject: Re: Normalizing Errors

From: gibsonian   

Date: 05 Jul 2006 22:48 EST

Good information on the problems with error-rates determined by Snowie and Gnu. As an "intermediate" player, I am not sure that I will be able to make use of this information, but am glad to be made aware that Doug might develop a means of "normalizing" a more effective means of error-rate determination.

You must be signed in to post comments.