I want to fit a series of lme() regression models that differ only in the
degrees of freedom of a ns() spline. I want to use a wrapper function to do
this. The models will be of the form
y ~ ns(x, df=splineDF)
where splineDF is passed as an argument to a wrapper function.
This works fine if the regression function is lm(). But with lme(),
I get an error. fitfunction() below demonstrates this.
Why?
KLUDGEfit() below provides a clumsy solution. It turns the lme()
command, along with the appropriate value of splineDF, into a text
string and then uses eval(parse(text=mystring)). But is there not a
more elegant solution?
set.seed(5)
junk<-data.frame(x=rnorm(100))
junk$y<-junk$x + rnorm(nrow(junk))
junk$idvar<- factor(sample(LETTERS[1:10], size=nrow(junk), replace=TRUE))
library("nlme")
library(splines)
fitfunction<-function(splineDF=1) {
thislm<-lm( y ~ ns(x, df=splineDF), data= junk)
thislm
cat("finished thislm\n")
thislme<-lme(
fixed= y ~ ns(x, df=splineDF)
, random= ~ 1 | idvar
, data= junk)
thislme
}
fitfunction()
KLUDGEfit<-function(splineDF=2) {
thislm<-lm( y ~ ns(x, df=splineDF), data= junk)
thislm
cat("finished thislm\n")
mystring<-paste(
"thislme<-lme( fixed= y ~ ns(x, df="
, splineDF
, "), random= ~ 1 | idvar , data= junk)"
, sep="")
eval(parse(text=mystring))
thislme
}
KLUDGEfit()
Thanks for any insight
Jacob A. Wegelin
Assistant Professor
Department of Biostatistics
Virginia Commonwealth University
830 E. Main St., Seventh Floor
P. O. Box 980032
Richmond VA 23298-0032
U.S.A.
______________________________________________
R-help@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.
