Date:         Thu, 7 Jul 2005 10:23:18 -0400
Reply-To:     Wensui Liu <liuwensui@gmail.com>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Wensui Liu <liuwensui@GMAIL.COM>
Subject:      Re: curve fitting
Comments: To: Richard <heteroliu@gmail.com>
In-Reply-To:  <1120741867.200350.260400@g49g2000cwa.googlegroups.com>
Content-Type: text/plain; charset=ISO-8859-1

proc nlin should do it. but you might not get a unique solution.

On 7/7/05, Richard <heteroliu@gmail.com> wrote:
> Dear SAS gurus,
>
> If I have the x, y data in pairs and know thier relation might look
> like y = a*exp(b*exp(cx-d)) where a, b, c, d are parameters, is there
> any procedure I can use to figure out the parameters to create a curve
> with the function for best fitting?
>
> Can proc genmod do this?
>
> Thank you for the generous answer in advance.
>
> Have a nice one.
>


--
WenSui Liu, MS MA
Senior Decision Support Analyst
Division of Health Policy and Clinical Effectiveness
Cincinnati Children Hospital Medical Center