[R] creating subsets within lm()

Thomas Groen tagroen at gmail.com
Thu Jul 30 12:04:20 CEST 2009


Dear All,

the lm() function has the possibility to create a subset of the
possible explaining variables that you have. However, in the help
there is no example how to use this subset option. I tried the
following:

model<-lm(dependent.data$MPFD~.,data=explaining.data,subset=c(1,0,0,0,0,0,0,0,1,1,0,0))

MPFD is the dependent variable stored in the data frame
dependent.data, and all 12 explaining variables are stored in the data
frame explaining.data.

However, this yields a model with only an intercept, and the comment

"Coefficients: (12 not defined because of singularities)"

I hope anyone would be able to give me an example how to do this correctly.

Kind regards,
Thomas




More information about the R-help mailing list