[ACT-R-users] (no subject)

[Dan Bothell]

--On Monday, February 23, 2004 10:01 AM +0000 A.Banks at surrey.ac.uk wrote:

> I have a quick newbie question which I wonder if anyone would be kind
> enough to help  me out with. When fitting models to data it seems quite
> common to estimate one or two  parameters in the model to maximise the
> fit; the fewer the better. What is the best or  the conventional method
> for doing this? The online tutorials imply that the  recommended approach
> is to try out different values until you get a good fit. But I'm
> concerned that with several parameters varying simultaneously I may not
> happen  across the optimal fit. Also, this doesn't seem particularly
> theoretically motivated. Is  there a better method?
>
> Thanks very much,
> Adrian
>

There was a symposium about model fitting at the ACT-R workshop
last year which you may find helpful, and the presentations are
available at:

<http://act-r.psy.cmu.edu/workshops/workshop-2003/schedule.html>

As for the tutorial, the reason that it presents the problems as
it does is because the objective is to give the student a feel
for how the parameters operate and what effects they have on the
the system.  That's not to say that modelers don't sometimes search
manually over the parameter space, but just why the tutorial doesn't
discuss other mechanisms one could employ.


Dan