[R] First Variable in lm

[Prof Brian Ripley]

It isn't lm but terms.formula.  Compare

terms(dat$y ~ .,data = dat)
terms(dat[, 1] ~ ., data = dat)

Now as to why, exactly, see the C code in src/main/model.c.
The short answer is that dat$y matches y, and dat[, 1] does not.
(I am not at all sure the first is intentional.)

On Wed, 24 Mar 2004, Baskin, Robert wrote:

> First: Thanks to everyone who develops R, maintains r-help, and participates
> in the list :)  
> 
> This is a silly follow up question.
> 
> >From Andy Liaw:
> > dat <- data.frame(y=rnorm(10), x1=rnorm(10), x2=rnorm(10))
> 
> (Silly question - if the answer is on the lm or formula help page I didn't
> get it:)
> Why does lm | formula treat dat[,1] slightly differently than dat$y?

-- 
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 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595