GARCH MODELS COMPARED TO CONNECTIONIST MODELS

[BHASKAR DASGUPTA ALIAS BD]

Hello,

I have a query about the suitability of using GARCH(p,q) models in modelling
economic and financial time series. I was advised to compare my NN
performance in foreign exchange rate prediction to the performance of a
GARCH model. I checked up in the Gershenfield & Weigend Book on Time Series
Forecasting, and in the chapter on Foreign exchange data series prediction
written by LeBaron, I could only find reference to a ARCH model used to
determine non-linearity along with the BDS and TSAY tests, but the ARCH
model was not used to predict or compare predictions.

Is this approach of comparing NN forecasts with GARCH models prevalent, or
is anyone working on this?, In the Trippi & Turban book, ARIMA models are
compared, but not GARCH/ ARCH. I am looking to contact someone who is
working on this, or someone who can guide me to some code which does this,
either as in a macro in LOTUS123, or RATS or SPSS (the only statistical
software I have access to :-). I would appreciate any response, and if there
are sufficient responses, I would summarize and repost to the group.

Thanks in advance.

bd


PS: I shall also be posting this message on the ALLSTAT group, so apologies
for the cross post.

Bhaskar Dasgupta

SnailMail
        Manchester Business School      Phone   ::010-44-61-275-6547
        Booth Street West               Fax     ::010-44-61-273-7732
        Manchester, M15 6PB, England.
email   ::b.dasgupta at fs3.mbs.ac.uk