Author: Dann Corbit
Date: 16:10:01 01/17/06
Go up one level in this thread
On January 17, 2006 at 18:38:43, Joseph Ciarrochi wrote: >>The above formula assmes that the relationship is linear > >Yes, I'm afraid so. Welcome to the simplified world of psychology:) > > We could test for other kinds of relationships. Maybe the key variable would be >a difference between black and white ELOS (this would simplify our analysis). >Then we could look for say, a logarithmic relationship between this difference >and performance. e.g., from 0 to 100 point difference, you get big difference in >predicted performance. In contrast, from 500 to 600 point difference, you get >little difference in predicted performance. You could also use a Levenberg-Marquardt fit though a large collection of elementary functions. At any rate, a linear estimation would probably provide good answers at least close to the solution points. And it is probably less prone to error.
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.