[19375] in s-news-athena
[S] xyplot
daemon@ATHENA.MIT.EDU (Winson Taam)
Fri Oct 1 12:12:09 1999
Date: Fri, 1 Oct 1999 12:00:13 -0400 (EDT)
From: Winson Taam <taam@Oakland.edu>
To: s-news@wubios.wustl.edu
Message-Id: <Pine.OSF.3.95.991001113435.19052D-100000@saturn2.acs.oakland.edu>
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
I would like to thank those who offered their answers to my question
regarding xyplot. Why STATSCI asks us to pay license maintanence fee
every year and it does not offer the same kind of service that
this news group provide?
Nick Ellis, John Thaden, Jose Pinheiro, Renard Lancelot, Robert Key
and Max Kuhn offered their help to my question. Thank you so much!
A great resource for learning xyplot or Trellis plot in general is
http://cm.bell-labs.com/cm/ms/departments/sia/project/trellis
I did not check but Jose Pinheiro indicated that there is a buildin
function in nlme 3.1 that augments predicted values. It is called
augPred().
Original problem was:
mydata.nlme <- nlme( .......,data=mydata,......)
xyplot( resp ~ expl | facA*facB,
data= mydata,
ylab='Response',
xlab='Explanatory',
panel=function(x,y) {
panel.xyplot(x,y)
yhat<- fitted(mydata.nlme)
panel.xyplot(x,yhat$population,type='l')
}
)
solution:
mydata.nlme <- nlme( .......,data=mydata,......)
yhat <- fitted(mydata.nlme)
xyplot( resp ~ expl | facA*facB,
data=mydata,
ylab='Response',
xlab='Explanatory',
panel=function(x,y,subscripts) {
panel.xyplot(x,y)
panel.xyplot(x,yhat$population[subscripts],type='p',pch='+')
}
)
Remarks:
*I did not use type='l' because the lines are wrapped around. It has
to do with sorting my facA*facB some how.
*The panel labels are different if I change facA & facB to numeric.
I will iron out some of these minor details. Thank you for all your
help.
Winson Taam
Department of Math. & Stat.
Oakland University
Rochester, MI 48309
tel: 248-370-3438
-----------------------------------------------------------------------
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
