Date:         Thu, 25 Jun 2009 06:01:19 -0700
Reply-To:     PeterHuang <peterhuang1981@GMAIL.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         PeterHuang <peterhuang1981@GMAIL.COM>
Organization: http://groups.google.com
Subject:      Re: SAS differential equations fitting problem
Comments: To: sas-l@uga.edu
Content-Type: text/plain; charset=ISO-8859-1

On Jun 24, 9:09 pm, Shankar <shankar.s...@gmail.com> wrote:
> hi Peter,
>
> You cannot have X in the FIT statement, as X is unobserved variable,
> i,e. you do
> not have data for X;
>
> However you can have the equation for derivative of X, it is treated
> as an auxillary equation;
>
> I tried the following:
>
> PROC MODEL DATA=sample maxiter=1000;
>
> dependent g 92 i 11;
>
> PARMS p1 .04 p2 .03 p3 .00001   n 0.3 gamma .3 h 8;
>
> bounds p1>0,p2>0,p3>0, 0<n<55, 0<gamma<0.5, h>0;
>
> DERT.G = -X*G+p1*(90-G);/* DEFINING THE EQUATION*/
>
> DERT.X = -p2*X+p3*(I-7);/* DEFINING THE EQUATION*/
>
> if G > h then DERT.I = -n*I+gamma*(G-h)*t;/* DEFINING THE EQUATION*/
> else DERT.I = -n*I;/* DEFINING THE EQUATION*/
>
> FIT G I/ TIME=t DYNAMIC;
>
> RUN;
> quit;
>
> The model converged and p1 , p2, p3 values are quite small; The
> results are very sensitive to initial guesses;
>
> Another thing: I took the values for p1 and other parameters that you
> think are correct, and ran the model using solve statement; The
> results do not match the data you have; I wonder if this is because
> parameters are not correct, or if the model is not correct, I do not
> know;
>
> Thanks,
> Shankar

Hi, Shankar,
Thanks for your help!

Thanks,
Peter