Hi all,
I think I've run into an error caused by my computer's having too little
computational power, but I'm not sure. I used the following code to
perform continuous registration on two functional objects:
lambda1 <- 10E-2
norder=8
samples<-seq(0,780,length=781)
nbasis <- length(samples)+norder-2
mybasis<-create.bspline.basis(c(0,780),nbasis,norder)
myfdPar<-fdPar(mybasis,4,lambda1)
myfd.unemployment <- smooth.basis(samples,unemployment.rate,myfdPar)$fd
myfd.unemployment.squared <- smooth.basis(samples,unemp.squared,myfdPar)$fd
lambda2<-10E-2
myfdPar<-fdPar(mybasis,4,lambda2)
myfd.inflation <- smooth.basis(samples,inflation.rate,myfdPar,)$fd
myfd.inflation.squared <- smooth.basis(samples,inflation.squared,myfdPar)$fd
plot(myfd.inflation)
#register
lambda=1
nbasis=myfd.unemployment$basis$nbasis
ntrial=1
y0fd=mean(myfd.inflation)
yfd=myfd.unemployment
coef0<-matrix(0,nbasis,ntrial)
wfd<-fd(coef0,mybasis)
wfdPar=fdPar(coef0,2,lambda)
reglist<-register.fd(y0fd,yfd,wfdPar,iterlim=10,dbglev=1)
I get the following error after the last command:
"Error in matrix(0, length(x), nbaspr) : too many elements specified"
Is this error associated with my computer's not having sufficient power to
perform the registration? I can't think of what else that might be going
on...
Thanks,
Zoe Richards
[[alternative HTML version deleted]]
______________________________________________
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.
