Date:         Fri, 16 May 2008 12:02:17 -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: Proc Nlin to fit 5 PL, how much the initial value matters ?
Comments: To: Ya Huang <ya.huang@amylin.com>
In-Reply-To:  <200805161551.m4GAnLL0012013@malibu.cc.uga.edu>
Content-Type: text/plain; charset=ISO-8859-1

hi, ya,
initial values of para. are important. but in your case, it seems you
have too many # of para. relative to # of cases.


> proc nlin data=xx outest=outparmsfull;
>  parms a=7 b=-1.25 c=7 d=93 g=1;
>     model y=d +( (a-d)/( (1+(x/c)**b)**g) );
> run;
>
===============================
WenSui Liu
Call for Donations for the China Earthquake!
Blog : statcompute.spaces.live.com
===============================