On 07/04/2018 06:14 PM, Joelle k. Akram wrote:

> Dear all,

>

>

> For a linear model I use the 'variogram' function in gstat as follows:

>

>

> coordinates(data) <- c('x','y')

> myvario <- variogram(dep~var1+var2+var3, data)

>

> Now, I have the following Nonlinear formula that I want to use in variogram.

>

> dep~ var1*var2^3

This is still a linear model.

>

>

> My 2 questions are:

>

> i) Can the variogram function in gstat handle nonlinear models as this formula?

>

> ii) What is the syntax to use this nonlinear formulae within the variogram function? is it simply :

>

> myvario <- variogram(dep~ var1*var2^3, data)

I think that like in other areas of R you'll have to use

myvario <- variogram(dep~ var1*I(var2)^3, data)

Note that the * will be interpreted as indicating you want main effects

and an interaction, not simply the product of var1*var3^3; see ?formula

--

Edzer Pebesma

Institute for Geoinformatics

Heisenbergstrasse 2, 48151 Muenster, Germany

Phone: +49 251 8333081

_______________________________________________

R-sig-Geo mailing list

[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo