[R] problem fitting 2 term exponential with nls

[William Dunlap]

> >> fit<-nls(d$time~a1*exp(b1*d$age) +
> > 	a2*exp(b2*d$age)+c
> > 	,start(a1=10,b1=0,a2=250,b2=1,c=0)
> 
> This line should read:  start=list(a1=10,b1=0,a2=250,b2=1,c=0)

After you fix that you will run into another problem
   Error in nls(d$time ~ a1 * exp(b1 * d$age) + a2 * exp(b2 * d$age) + c,  : 
     parameters without starting value in 'data': age
Instead of using d$time and d$age, use data=d and just time and age:
fit<-nls(data=d, time~a1*exp(b1*age) + a2*exp(b2*age)+c 
     ,start=list(a1=10,b1=0,a2=250,b2=1,c=0)
     ,trace=T)

Bill Dunlap
Spotfire, TIBCO Software
wdunlap tibco.com


> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] On Behalf
> Of Berend Hasselman
> Sent: Friday, October 25, 2013 9:54 PM
> To: Tom Wright
> Cc: r-help at stat.math.ethz.ch
> Subject: Re: [R] problem fitting 2 term exponential with nls
> 
> 
> On 25-10-2013, at 17:29, Tom Wright <tom at maladmin.com> wrote:
> 
> > Hi,
> > Can anyone explain why the nls function is giving an error?
> > Thanks
> > Tom
> >
> >> head(d)
> >        age  time
> > 1 23.566667 223.0
> > 2 42.633333 223.0
> > 3 62.300000 222.0
> > 4 32.933333 220.5
> > 5  9.366667 228.0
> > 6 23.833333 227.0
> >
> >> fit<-nls(d$time~a1*exp(b1*d$age) +
> > 	a2*exp(b2*d$age)+c
> > 	,start(a1=10,b1=0,a2=250,b2=1,c=0)
> 
> This line should read:  start=list(a1=10,b1=0,a2=250,b2=1,c=0)
> 
> Berend
> 
> > 	,trace=T)
> > Error in hasTsp(x) : argument "x" is missing, with no default
> >
> > ______________________________________________
> > R-help at r-project.org mailing list
> > https://stat.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> > and provide commented, minimal, self-contained, reproducible code.
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.