Message-ID: <199709152210.KAA24228@stat1.stat.auckland.ac.nz>
Date: 1997-09-15T22:10:52Z
From: Ross Ihaka
Subject: R-alpha: predict.lm -- who ..?
In-Reply-To: <x2yb4yckb5.fsf@bush.kubism.ku.dk>
Peter Dalgaard BSA writes:
> "predict.lm" <- [stuff returning a data frame]
This looks just like what I had in mind (though I was thinking matrix
rather than dataframe). This I think is more useful (at least to the
kiddies I teach) than the S one.
BUT: I have been berated by my class for preparing examples with R and
trying to pass them off as S - they notice the minor differences.
Pehaps it would be possible to make a library "smodels" which is as
close to S as we can make it. I have an lm.summary and
lm.summary.print which could go into it.
In general I don't like compatibility boxes, but this seems harmless
enough.
Ross
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
r-devel 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-devel-request@stat.math.ethz.ch
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-