[R] How to get objects from a "formula" specification?

Ravi Varadhan rvaradha at jhsph.edu
Fri Dec 13 19:50:26 CET 2002


I'd like to thank Prof. Ripley and Andy Liaw for their solution to my 
question. They suggested using "model.frame" or "model.matrix"

Best,
Ravi.
----- Original Message -----
From: ripley at stats.ox.ac.uk
Date: Friday, December 13, 2002 12:44 pm
Subject: Re: [R] How to get objects from a "formula" specification?

> ?model.frame
> ?model.matrix
> 
> `S Programming' by Venables & Ripley (2000).
> 
> On Fri, 13 Dec 2002, Ravi Varadhan wrote:
> 
> > Hi:
> >
> > I'd like to get the objects corresponding to the elements in a 
> formula,> from a data frame.  For example, suppose I would like to 
> make a
> > function call, such as follows:
> >
> > myfunc(formula="y ~ x1 + x2 + log(x3)" , data=mydata)
> >
> > This function will get the vector objects y, x1, x2, and log(x3) 
> from> the data frame "mydata" to form the design matrix and then 
> perform a
> > maximum likelihood estimation of the regression parameters.
> >
> > My questions is,  how do I get the the vector objects y, x1, x2, and
> > log(x3),specified the formula, from the data frame "mydata"?
> 
> BTW, that's not precisely how formulae in R work.
> 
> -- 
> Brian D. Ripley,                  ripley at stats.ox.ac.uk
> Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
> University of Oxford,             Tel:  +44 1865 272861 (self)
> 1 South Parks Road,                     +44 1865 272860 (secr)
> Oxford OX1 3TG, UK                Fax:  +44 1865 272595
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> http://www.stat.math.ethz.ch/mailman/listinfo/r-help
>




More information about the R-help mailing list