[R] relaimpo

[Jyotin Modha]

Hello,

Does anyone know if relaimpo only applies to pure multiple linear
regression models, i.e.

 

-  linear in the variables AND linear in the coefficients

 

or is it safe to use it in models that are:

 

-  non-linear in the variables BUT linear in the coefficients?

 

Thanks

 

Jyotin 

 


[[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.

[R] relaimpo - dummy variable

[Gabriela Bucini]

Hi,

I have a question related to the function boot.relimp (package relaimpo).

I have a model with numerical predictors and one dummy (class) variable. I
would like to calculate the relative importance of the predictors but I have
some problems with the dummy variable.

The name of the linear model is lmbroadst.lc and the dummy variable is
datacon.landcover_gb (with 7 levels). I write the command as:

boot - boot.relimp(lmbroadst.lc, b = 500, type = c(lmg, last, first),
rank = TRUE, group = datacon.landcover_gb,
  diff = TRUE, rela = TRUE)

The error message is:

Error in boot.relimp.lm(lmbroadst.lc, b = 500, type = c(lmg, last,  :
  argument 5 matches multiple formal arguments


What is the correct syntax to include the dummy variable?

Thank you very much for your help!

Gabriela Bucini

__
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.