Most of my analyses are Panel/TSCS analyses with fairly long monthly or weekly series. Is it possible in the EViews Panel/TSCS framework to get multiplicative seasonality [(1 - Phi1 B1)(1 - Phi12B12)] or is one restricted to additive seasonality [(1 - Phi1B1 - Phi12B12 - Phi13B13)]?
Thanks for your help.
Matt
Seasonality in EViews Panel/TSCS Analyses
Moderators: EViews Gareth, EViews Jason, EViews Moderator, EViews Matt
-
- Fe ddaethom, fe welon, fe amcangyfrifon
- Posts: 13318
- Joined: Tue Sep 16, 2008 5:38 pm
Re: Seasonality in EViews Panel/TSCS Analyses
I believe SAR terms will do what you want. You should double check by looking in the Seasonal ARMA terms part of User Guide II.
Follow us on Twitter @IHSEViews
-
- Posts: 7
- Joined: Thu Jan 29, 2009 9:59 am
Re: Seasonality in EViews Panel/TSCS Analyses
Thanks for your reply, Gareth.
I tried the SAR() approach. However, since my data are in a pooled format, EViews didn't like it and complained that SAR() terms cannot be used within a system. I haven't yet tried the SAR() approach with TSCS data that are in stacked form. At least for pooled TSCS analyses, it looks like stochastic seasonality is limited to the additive form.
Matt
I tried the SAR() approach. However, since my data are in a pooled format, EViews didn't like it and complained that SAR() terms cannot be used within a system. I haven't yet tried the SAR() approach with TSCS data that are in stacked form. At least for pooled TSCS analyses, it looks like stochastic seasonality is limited to the additive form.
Matt
Who is online
Users browsing this forum: No registered users and 39 guests