s-news
[Top] [All Lists]

Re: Regressing by Rolling Time

To: "'ng singlan'" <singlan4rock9@yahoo.com>, <s-news@lists.biostat.wustl.edu>
Subject: Re: Regressing by Rolling Time
From: "Eric Zivot" <ezivot@u.washington.edu>
Date: Thu, 18 May 2006 10:47:40 -0700
Importance: Normal
In-reply-to: <20060518063027.13834.qmail@web36207.mail.mud.yahoo.com>
Organization: University of Washington

The splus function aggregateSeries together with the lm function can be used to do the rolling regression you describe. The lme and nlme libraries have functions for panel data regression.

 

-----Original Message-----
From: s-news-owner@lists.biostat.wustl.edu [mailto:s-news-owner@lists.biostat.wustl.edu] On Behalf Of ng singlan
Sent: Wednesday, May 17, 2006 10:30 PM
To: s-news@lists.biostat.wustl.edu
Subject: [S] Regressing by Rolling Time

 

Hi,

 

Does anyone know that can S-Plus handle Regression by Rolling Time? For example, analyzing data for a time period of say May 2001-May 2006, then for a time period of Jun 2001-Jun 2006, then for a time period of July 2001-July 2006.

 

I know that S-Plus FinMetrics can do for a time period of say from May 2001-May 2006, then for a time period from May 2001- Jun 2006, then for a time period from May 2001-July 2006, which the end date is increasing but the start date is still the same. But i need to do the regression which both of the start date and end date is increasing(+1)

 

I would like to know also can S-Plus handle panel data and cross sectional time regression.

 

Thank you.

 

Best Regards,

NSL


Sneak preview the all-new Yahoo.com. It's not radically different. Just radically better.

<Prev in Thread] Current Thread [Next in Thread>