[18784] in s-news-athena
[S] gam prediction
daemon@ATHENA.MIT.EDU (Xu Fan)
Thu Jul 29 12:37:06 1999
Date: Thu, 29 Jul 1999 12:31:12 -0400 (EDT)
From: Xu Fan <fan@stat.cmu.edu>
To: s-news@wubios.wustl.edu
Message-Id: <Pine.HPP.4.10.9907291223571.5732-100000@sloth.stat.cmu.edu>
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
I encountered some surprises when using fitted gam object to
predict based on new regressor values. It might be due to some simple
grammar mistakes.
mod <- gam(ozone^(1/3) ~ lo(radiation) + lo(wind, temperature), data =
air)
newdata <- data.frame(ozone=4,radiation=200,temperature=70,wind=8)
predict.gam(mod,data=newdata)
# why do I get 111 outputs? I expect a single output corresponding to
# the new regressors feeded.
predict.gam(mod, data=air[1,])
# still 111 outputs.
-----------------------------------------------------------------------
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
