[R] lm Help!!

Prof Brian D Ripley ripley at stats.ox.ac.uk
Wed Apr 12 10:02:15 CEST 2000

On Tue, 11 Apr 2000, Kenneth Cabrera wrote:

> Hi, everybody!!
> How can I calculate the Type III ss, as defined by SAS, for a linear regresion?

With considerable difficulty, deliberately so.  Type III ss ignore the
hierarchy of the terms that all the S/R formula calculations insist on.
S-PLUS has a way to do this, but it is much berated. S has a bug in drop1
that can be used to fake type III ss's, but R has not copied that bug.

The only way I know to do this in R is to pick apart model matrices and fit
sub-models for each line.  But then as (a) I think it is statistical
nonsense and (b) I know how to do in S-PLUS, I have not tried to do it in

> How can you use apply with a function that have several parameters like "plot"?

You can pass additional argument in ..., as in the example (cave) on the
help page.  If you want to vary more than one argument, write a wrapper
function (which you can always do) and use that in the call to apply.

If that is not clear enough, please give us an explicit example of what you
are want to do.

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

More information about the R-help mailing list