[R] Question concerning functions nlsList and nlme from nlme R library.

[Jens_Praestgaard@hgsi.com]

I hope that the mailing list is the correct forum for the question below. I
have trouble calling functions nlsList and nlme from
another function. Any help would be greatly appreciated.

Jens Praestgaard
Human Genome Sciences
Rockville MD.



I have a data set v with two components, v$mixeddat and v$init. They are
listed below:

> v$mixeddat
           conc result rep sample z
11  20.00000000  11141   1 vial 1 0
12   5.00000000  11446   1 vial 1 0
13   1.25000000  13377   1 vial 1 0
14   0.31250000  20267   1 vial 1 0
15   0.07812500  48852   1 vial 1 0
16   0.01953125 118507   1 vial 1 0

(and so on)

> v$init
           a            b            d            c        cdiff
1.045617e+04 2.408045e+05 9.296929e-01 1.490621e-02 4.874540e-03

The following two lines of code fits first a nonlinear regression for each
level of rep, next a model with a random effect in one parameter.

> fit<-nlsList(result~a+(b-a)/(1+(conc/(c+z*cdiff))^d)
|rep,start=v$init,data=v$mixeddat)
> nlme(fit,random=(b~1))


However, when I try to run the same code  from within a function, with this
call :

> testfunc
function(dat=v) {
test<-nlsList(result~a+(b-a)/(1+(conc/(c+z*cdiff))^d)
|rep,start=dat$init,data=dat$mixeddat)
return(nlme(test,random=b~1))
}

testfunc()

then I get the error message

Error in eval(expr, envir, enclos) : Object "result" not found



 Any help would be appreciated