I am not sure if it is possible to provide a data set sufficient to fit this
model and reproduce the error. However, I noticed that the warnings no
longer show up when the number of predictors for b0 and b1 in b0~ and
b1 ~ is small (3 to 5). Could this be an effect too many
"subcoefficien
I am using the gnls procedure in nlme package to fit a nonlinear model as:
nl.fit<-gnls(Y ~ b0*exp(b1/X),
data = data1,
params=list(
b0~p1+I(p1^2)+p2+I(p2^2)+p3+I(p3^2)+p5+p6
b1~p8+p2+I(p2^2)+p3+p9+p10+p11),
star
2 matches
Mail list logo