Awesome! Thanks. Is that the reason why I seem to have seen people ask about adding an ARMA process and a GARCH process? I'll surely look at that text.
On Thu, Oct 1, 2009 at 4:49 PM, John C Frain <frainj(a)gmail.com> wrote: > An ARIMA model is basically a model of the level of the process. A > GARCH model is a model of the volatility of the process. There can of > course be interactions between the volatility and the level (e.g. > Garch in mean process). A complete answer to your questions would > take an email equivalent to several chapters in a book. One uses the > log of a variable when one sees the shock to the process as being > multiplicative. I would think that the shock process in > multiplicative for most price processes. > > Might I recommend a text such as Enders or similar as an introduction > to time series analysis. > > Best Regards > > John > > 2009/10/1 Saqib Ilyas <msaqib(a)gmail.com>: > > Hi all, > > I tried sending this email last night, but I don't think it has gotten > > through. Perhaps my membership hadn't been processed as yet. > > > > I am using the 2006 till 2009 data for the New England pool of day-ahead > > weighted average prices. I am not very fluent with econometrics, but I > read > > in some papers that GARCH has been used successfully to forecast > electricity > > wholesale prices. When I train a GARCH model on one year worth of data, > and > > forecast for the last 3 days of training data, I get a mean absolute > error > > of 3.6642%. The error increases to 27.826% when I use two years worth of > > data, and decreases to 17.123% when using three years worth of past data. > Is > > this expected? > > > > Also, when I plot the actual and fitted data against time, the GARCH > model > > seems to have done a really bad job, compared to a default ARIMA model. > I'm > > guessing this might be because people are actually using ARIMA models > with > > (added) GARCH errors, so a simple GARCH model-based forecast isn't doing > > exactly what they have done. Am I right? Why would the ARIMA be a better > fit > > than GARCH? > > > > One author mentioned that they took a log of the prices (in their case it > > was hourly prices) before fitting a GARCH model. In your opinion, is that > an > > important factor in the kind of errors I am getting? > > Thanks and best regards > > -- > > Muhammad Saqib Ilyas > > PhD Student, Computer Science and Engineering > > Lahore University of Management Sciences > > _______________________________________________ > > Gretl-users mailing list > > Gretl-users(a)lists.wfu.edu > > http://lists.wfu.edu/mailman/listinfo/gretl-users > > > > > > -- > John C Frain > Economics Department > Trinity College Dublin > Dublin 2 > Ireland > www.tcd.ie/Economics/staff/frainj/home.html > mailto:frainj(a)tcd.ie > mailto:frainj(a)gmail.com > _______________________________________________ > Gretl-users mailing list > Gretl-users(a)lists.wfu.edu > http://lists.wfu.edu/mailman/listinfo/gretl-users > -- Muhammad Saqib Ilyas PhD Student, Computer Science and Engineering Lahore University of Management Sciences
Awesome! Thanks. Is that the reason why I seem to have seen people ask about adding an ARMA process and a GARCH process?
I'll surely look at that text.
On Thu, Oct 1, 2009 at 4:49 PM, John C Frain <fra...@gmail.com> wrote:
An ARIMA model is basically a model of the level of the process. A
GARCH model is a model of the volatility of the process. There can of
course be interactions between the volatility and the level (e.g.
Garch in mean process). A complete answer to your questions would
take an email equivalent to several chapters in a book. One uses the
log of a variable when one sees the shock to the process as being
multiplicative. I would think that the shock process in
multiplicative for most price processes.
Might I recommend a text such as Enders or similar as an introduction
to time series analysis.
Best Regards
John
2009/10/1 Saqib Ilyas <msa...@gmail.com>:
> _______________________________________________> Hi all,
> I tried sending this email last night, but I don't think it has gotten
> through. Perhaps my membership hadn't been processed as yet.
>
> I am using the 2006 till 2009 data for the New England pool of day-ahead
> weighted average prices. I am not very fluent with econometrics, but I read
> in some papers that GARCH has been used successfully to forecast electricity
> wholesale prices. When I train a GARCH model on one year worth of data, and
> forecast for the last 3 days of training data, I get a mean absolute error
> of 3.6642%. The error increases to 27.826% when I use two years worth of
> data, and decreases to 17.123% when using three years worth of past data. Is
> this expected?
>
> Also, when I plot the actual and fitted data against time, the GARCH model
> seems to have done a really bad job, compared to a default ARIMA model. I'm
> guessing this might be because people are actually using ARIMA models with
> (added) GARCH errors, so a simple GARCH model-based forecast isn't doing
> exactly what they have done. Am I right? Why would the ARIMA be a better fit
> than GARCH?
>
> One author mentioned that they took a log of the prices (in their case it
> was hourly prices) before fitting a GARCH model. In your opinion, is that an
> important factor in the kind of errors I am getting?
> Thanks and best regards
> --
> Muhammad Saqib Ilyas
> PhD Student, Computer Science and Engineering
> Lahore University of Management Sciences
> Gretl-users mailing list
> gretl-us...@lists.wfu.edu
> http://lists.wfu.edu/mailman/listinfo/gretl-users
>
--
John C Frain
Economics Department
Trinity College Dublin
Dublin 2
Ireland
www.tcd.ie/Economics/staff/frainj/home.html
mailto:fra...@tcd.ie
mailto:fra...@gmail.com
_______________________________________________
Gretl-users mailing list
gretl-us...@lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users
--
Muhammad Saqib Ilyas
PhD Student, Computer Science and Engineering
Lahore University of Management Sciences