A general comment, 23 observations for an ARIMA model is not enough for estimation, 50 or higher may be better.
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On Behalf Of Mesut Gunes
Sent: Monday, May 04, 2009 3:46 PM
To:
[hidden email]
Subject: Time Series Modeler
Hi everyone,
I am currently studying on forecasting for short term electrical energy
demand and i have 23 months of consumption data. I am using SPSS 17 >
Analyze > Forecasting > Create Model
then SPSS suggests models for each months almost all of them are Winter's
Multiplicative because of the double seasonality but the problem is that
many of the p-values of Ljung-Box Q test are less than 0.05, but 3 of them
are significant.
if i apply the menu again with selecting the elimination of outlier, this
time 10 of them are significant. Totally 11 months are significant.
eventually, i could not find adequate models for every moths.
I want to learn that what is the criteria of selecting model in SPSS 17 Time
Series Modeler?
Any suggestion for my work?
Will i make a big mistake if i ignore the p-values of Ljung-Box Q test, and
go ahead with the models spss suggests?
Best Regards
Mesut.
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
NOTICE: This e-mail (and any attachments) may contain PRIVILEGED OR CONFIDENTIAL information and is intended only for the use of the specific individual(s) to whom it is addressed. It may contain information that is privileged and confidential under state and federal law. This information may be used or disclosed only in accordance with law, and you may be subject to penalties under law for improper use or further disclosure of the information in this e-mail and its attachments. If you have received this e-mail in error, please immediately notify the person named above by reply e-mail, and then delete the original e-mail. Thank you.
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Locked
