Re: ANN vs. nonlinear regression: forecasting

[Joe Ward]

John --

 

Sounds very interesting--

 

If you mean "classical" least-squares model, there are no assumptions involved

in fitting least-squares. It's only the "statistics" assumptions that get added into

the extra "assumptions".

 

PREDICTION is the important thing. 

Compare the PREDICTIVE accuracy/costs/etc.of various approaches.

 

You may wish to include RESAMPLING/BOOTSTRAP/CROSS-VALIDATION

in your research. 

 

 The proof of the "best" is how well it PREDICTS

 

I will be interested in what you learn.

 

-- Joe

************************************************************************
* Joe Ward                                  Health Careers High School *
* 167 East Arrowhead Dr                     4646 Hamilton Wolfe        *
* San Antonio, TX 78228-2402                San Antonio, TX 78229      *
* Phone: 210-433-6575                       Phone: 210-617-5400        *
* Fax: 210-433-2828                         Fax: 210-617-5423          *
* [EMAIL PROTECTED]                                                    *
* http://www.ijoa.org/joeward/wardindex.html                           *
************************************************************************

 

 

----- Original Message -----

From: <[EMAIL PROTECTED]>

To: <[EMAIL PROTECTED]>

Sent: Friday, February 11, 2000 7:01 AM

Subject: ANN vs. nonlinear regression: forecasting

| I'm working on a study that compares neural networks to classical non-
| linear statistical estimators in forecasting time series.  My thesis is
| that the NN would be robust under conditions where the assumptions of
| the classical model are not met, and the nn would be inferior where the
| classical assumptions are satisfied.
|
| What would be a good classical model to compare a neural network to?
| Does anyone know of any papers/sources on this subject?
|
| I sincerely appreciate any help/suggestions.
|
| John Carrier
| [EMAIL PROTECTED]
|
|
| Sent via Deja.com http://www.deja.com/
| Before you buy.
|
|
| ===========================================================================
|   This list is open to everyone. Occasionally, people lacking respect
|   for other members of the list send messages that are inappropriate
|   or unrelated to the list's discussion topics. Please just delete the
|   offensive email.
|
|   For information concerning the list, please see the following web page:
|   http://jse.stat.ncsu.edu/
| ===========================================================================
|