R help - Feb 2010 - Issue with the package dyn used together with the function loess

Hi,

I am trying to use package dyn together with loess. I have the following
issue in the code below when I use "predict" while specifying the
"newdata"
argument.

Any help is welcomed. Thanks in advance.


Matthieu Cornec
> y <- ts(1:12, start = c(2000,2), freq = 4)^3
> x <- ts(1:9, start = c(2000,3), freq = 4)^2
> do<-cbind(x,y)
> rm(x)
> rm(y)
> y.loess <- dyn$loess( y ~ diff(x) ,data=do)
> predict(y.loess)
          Qtr1      Qtr2      Qtr3      Qtr4
2000                                27.71035
2001  62.14381 125.00000 216.00000 343.00000
2002 512.00000 730.85619 999.29512
> predict(y.loess,do)
Erreur dans newx/rep(divisor, rep(M, D)) :
  argument non numérique pour un opérateur binaire

(which translation should be Error in newx/rep(divisor, rep(M, D)) :
  non-numeric argument for a binary operator)

	[[alternative HTML version deleted]]