Hi,
I am creating a model with loess but predict complains about missing
variables. This doesn't help with single variable formulas or with lm with
any formula. Looks like a bug to me
# doesn't work
> l = loess(y ~ log(x) + log(z) , data.frame(z = 1:100, x=1:100 +
rnorm(100), y=1:100))
> predict(l, data.frame(x=1:100, z=1:100))
Error in predict.loess(l, data.frame(x = 1:100, z = 1:100)) :
'newdata' does not contain the variables needed
#works with lm
> l = lm(y ~ log(x) + log(z) , data.frame(z = 1:100, x=1:100 + rnorm(100),
y=1:100))
> predict(l, data.frame(x=1:100, z=1:100))
1 2 3 4 5 6
7 8 9 10 11 12
-53.790533 -33.916997 -22.291724 -14.043461 -7.645611 -2.418188 2.001536
5.830075 9.207086 12.227925 14.960606 17.455348
[...]
#works with simpler formula
l = loess(y ~ log(x) , data.frame(z = 1:100, x=1:100 + rnorm(100), y=1:100))
> predict(l, data.frame(x=1:100))
[1] 3.213052 5.524131 19.785356 54.505929 NA NA
NA NA NA NA NA NA NA
[14] NA NA NA NA NA NA
NA NA NA NA NA NA NA
[...]
Suggestions? Thanks
A
[[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.
