David,
In my opinion this is a very bad model. There is no justification whatsoever
for a seasonal differencing of order 6 for the time series that you analyzed
using SPSS. Furthermore there are more egregious outliers/interventions than
the one at time period "10".
Hope this helps.
Dave Reilly
Senior Vice President
Automatic Forecasting Systems
www.autobox.com
215-675-0652 (office)
215-353-7087 (cell)
-----Original Message-----
From: A UK-based worldwide e-mail broadcast system mailing list
[mailto:[log in to unmask]] On Behalf Of [log in to unmask]
Sent: Thursday, December 10, 2009 10:11 AM
To: [log in to unmask]
Subject: SPSS Time Series Output
I hope someone can help or direct me somewhere useful
I have a table from SPSS Time Series Analysis -version 16. I can confirm the
periodicity of the data is 12 as it is monthly.
I have an ARIMA model with Seasonal Differencing. It says 1 under the
estimate heading i.e. one degree of seasonal differencing. But what does a
figure of 6 mean earlier in the row?
There is another row with similar information at the end which refers to a
significant intervention variable. Again, what does a 10 mean here?
Excuse ignorance
Dr David Pitfield AcSS
Senior Lecturer
Transport Studies Group
Room RT008
Department of Civil and Building Engineering
Loughborough University
Loughborough
Leicestershire LE11 3TU
UK
Phone +44 1509 223416
Fax +44 1509 223981
Email [log in to unmask]
URL : http://www.lboro.ac.uk/departments/cv/staff/profile/38.html
Home:
Lings Farm
47 Main Street
Keyworth
Nottingham NG12 5AA
UK
Phone +44 115 9374922
Cell +44 7765 783300
Email [log in to unmask]
|