Hi Riza and all,
John L. Casti's book (Would-be worlds) has a number of
tips on how to understand models in general; I found
that adapting some of his ideas I could "feel" better
if my models were more or less correct.
Depending on your problem, you can also use techniques
such as the one described in John L. Miller's
article "Active Nonlinear Tests of Complex Simulation
Models".
Remember that ultimately what you may be trying to test
is the adequability of the model to the world you are
trying to capture; and most of the time, only an
experienced person on the subject can answer that.
- -Jeff
Quoting riza <riza@mail.ukans.edu>:
> Dear colleagues:
>
> We have been working on a project that involves the use of Bayes Nets to
> model financial returns. However, we are not sure about how to test our model,
> (if this is possible at all). We know there are a number of applications of
> Bayes Nets in different contexts, so we will be grateful if anyone can suggest
> any references on testing Bayes Net models.
>
> Thank you very much in advance.
>
> Riza Demirer
> PhD Candidate
> University of Kansas
>
This archive was generated by hypermail 2b29 : Mon Feb 25 2002 - 11:29:45 PST