Date:         Fri, 1 Dec 2006 22:37:16 -0300
Reply-To:     rdporto1 <rdporto1@TERRA.COM.BR>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         rdporto1 <rdporto1@TERRA.COM.BR>
Subject:      Re: SAS/ETS without ETS
Comments: To: rhmcom <rhmcom@GMAIL.COM>
Content-Type: text/plain; charset=iso-8859-1

Hi rgds, :-)

you have to do it partially. PROC REG has a
DW option that you can use to analyze the
first order autocorrelation. For a Ljung-Box
type test, you could use PROC FREQ and
your residuals. Of course, you'll have some
troble to program it and make sure you don't
make any error...

Good luck.

Rogerio.

---------- Cabeçalho original -----------

De: "SAS(r) Discussion" SAS-L@LISTSERV.UGA.EDU
Para: SAS-L@LISTSERV.UGA.EDU
Cópia:
Data: Fri, 1 Dec 2006 14:10:10 -0800
Assunto: SAS/ETS without ETS

> Hi,
>
>  I would like to do AR modeling but my company doesn't have SAS/ETS,
> but only SAS/STAT.
> Do you have any suggestion in order to proceed to non autocorrelation
> test ?
>
> rgds
>