"Rajarshi Guha" <[EMAIL PROTECTED]> wrote in message
news:[EMAIL PROTECTED]
> Hello,
>   I was wondering whether anybody whould be able to help with this query.
>
>
> I have some neural network models which makes predictions for a dataset.
When
> comparing various models we evalute the effectiveness by looking the RMS
> error and the value of R^2 between the predicted and actual values.
>
> However, I seem to have read somewhere that R^2 is not always a 'good
> indicator' - in that a data set can be randomly generated yet show a good
> R^2. Is this true? And if so, does anybody know how I can reference this
> (paper/book)?
>
> Thanks,
> Rajarshi
----------------------------------------------------------------------------
-------------------------------
I would also suggest you look into structural equation modeling (SEM), since
this is a big field. The equations are basically covariance/correlation
based, and use maximum likelhood methods to fit models to data. For a data
matrix pxn, where p is the number of variables, up to p*(p+1)/2 parameters
can be fitted.  The method gives rise to many model fit parameters, chiefly
Chi-Square based. There have been papers on differenent ways to arrive at a
p value from correlation values.

David Heiser


.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to