[R] lm with data=(means,sds,ns)

[(Ted Harding)]

On 18-Apr-04 Peter Dalgaard wrote:
> However, it begs the question whether it wouldn't have been better
> to design the RSS into the lm class rather than computing it from
> residuals in summary.lm and anova.lm and predict.lm and...

Well, something like this though lay under my original query.
The 'lm' fit, as opposed to 'glm' where for some models it
may be necessary to work from individual observations, is
basically least-squares, so it could be done once and for
all as Peter suggests. Hence I wondered if this had somehow
already been implemented (not necessarily in the 'lm' function
itself).

It does seem more logical to "design the RSS into the lm class".

Best wishes,
Ted.


--------------------------------------------------------------------
E-Mail: (Ted Harding) <Ted.Harding at nessie.mcc.ac.uk>
Fax-to-email: +44 (0)870 167 1972
Date: 18-Apr-04                                       Time: 13:06:48
------------------------------ XFMail ------------------------------