[19153] in s-news-athena
Re: [S] Is it possible to predict on supsmu?
daemon@ATHENA.MIT.EDU (Prof Brian D Ripley)
Wed Sep 8 17:12:37 1999
Date: Wed, 8 Sep 1999 22:05:54 +0100 (BST)
From: Prof Brian D Ripley <ripley@stats.ox.ac.uk>
To: "H.B. Jiu" <hbjsplus@hotmail.com>
Cc: s-news@wubios.wustl.edu
In-Reply-To: <19990908193804.67113.qmail@hotmail.com>
Message-Id: <Pine.GSO.4.05.9909082202350.3732-100000@auk.stats>
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
On Wed, 8 Sep 1999, H.B. Jiu wrote:
>
> Hi. I was wondering if it's possible to do a predict() on the result from a
> supsmu() operation. lm() and loess() are fine, but not supsmu()?
Not directly (and lots of other functions do not have predict methods).
You can use approx on the output of supsmu to do linear interpolation,
which should suffice.
If you really want a sophisticated way to do this there is a version of
supsmu with a predict method in Fortran buried in my ppr function (now in
library MASS). But I wouldn't use that unless you have a lot of this to do
(ppr does).
--
Brian D. Ripley, ripley@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
-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news
