[R] lm methods inconsistency?

[Prof Brian D Ripley]

On 10 Jan 2000, Tomislav Goles wrote:

> 
> I'm very new to R so maybe i'm doing something wrong so
> please let me know it that is that case.
> Here is an example where the summary() and residuals()
> applied to lm object produce different results
> (I think the residuals() results is correct since SAS produces
> those numbers - the second residual corresponding to observation
> with weight 4 is wrong in summary()).
> 
> x <- c( 10, 20, 30, 40 )
> y <- c( 33.8, 62.2, 92.0, 122.4 )
> w <- c( 1, 4, 1, 1 )
> lm.obj <- lm( y ~ x, weights=w )
> print( summary( lm.obj ) )
> print( residuals( lm.obj ) )

It's the documentation that is wrong. R follows S, which says for
summary.lm:

residuals:     the  model  residuals.   These  are  the  weighted
       residuals if weights were given in the model.

The function weighted.residuals gives those directly.

> PS. my version or R is 0.64.2 on Linux.

Well, we have had four versions since then, and many, many bugs have been
fixed.


-- 
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 mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._