Hello! Trying to fit a non linear regression model modF<-nlsModel(kf~3*alpha*epsilon^P, dat, list(alpha=ALPHA)) I get the error message "Error in numericDeriv(form[[3]], names(ind), env) : cannot allocate vector of length 1098922500"....I do not uneerstand as each of the above vectors kf, alpha, epsilon have equal length (31 500) and P is a constant It is probably a trivial error, but I'm stuck! Thanks Anne [[alternative HTML version deleted]]
anne <anne.piotet at urbanet.ch> writes:> Hello! > > Trying to fit a non linear regression model > > modF<-nlsModel(kf~3*alpha*epsilon^P, dat, list(alpha=ALPHA))You should use nls, not nlsModel. Also, if P is fixed then this is a linear regression model. Why use nonlinear regression.