Date:         Thu, 14 Oct 1999 11:47:49 -0400
Reply-To:     michael.helms@duke.edu
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Michael Helms <mjhelms@DUKE.EDU>
Organization: Duke University, Durham, NC, USA
Subject:      Re: Constrained Max.Likelihood in SAS.
Content-Type: TEXT/PLAIN; charset=US-ASCII

On 13 Oct 1999, Tirthankar C.P wrote:

>
> Dear SAS-Lers,
>
>  Is it possible to do constrained max. likelihood estimation in SAS ?
>
>         Is it possible using proc arima ?
>
>         Please point me to any solution in the manuals or any programs.
>         Programs would be better.
>
>
> TIA,
>
> Tirthankar
>
> Tirthankar C.P
> Research Student
> Indira Gandhi Institute of Development Research    Phone:91-022-840 0919/20/21
> Goregaon East                                        Fax:  91-022-8402027
> Mumbai 400 065                                     email:-tir@igidr.ac.in
> India.
>
> "Reality is merely an illusion, albeit a very persistent one."
>                                                               -Albert Einstein
> ________________________________________________________________________________
>

You may also wish to check with the documentation of Proc NLIN; a number
of different maximum likelihood techniques are available, and various
constraints can be built into the fit, depending on the technique and the
assumptions you feel justified in making.
                                           Mike

 Michael J. Helms                Div. of Behavioral Medicine
 mjhelms@acpub.duke.edu          Box 2969 DUMC
 (919)684-2774 W                 Duke University Medical Center
 (919)682-6722 W                 Durham, NC 27710