Message-ID: <Pine.SOL.3.96.1030606103805.20906A-100000@moon.stats.gla.ac.uk>
Date: 2003-06-06T09:45:56Z
From: Simon Wood
Subject: partial residuals in plot.gam()
In-Reply-To: <5.2.1.1.0.20030605185915.03efe258@pop3.norton.antivirus>
> I know a partial residual option in plot.gam() is on Simon Wood's todo
> list, but since I'm in the midst of a project and not yet having acquired
> sufficient R knowledge to code something usable myself I'll have to put my
> trust in you. Anybody got some code lying around for doing this? Or if
> someone can supply me with enough hints for doing it myself, I'd be most
> grateful.
- sorry partial residuals still no done, but here's a `do-it-yourself'
example....
# set up a simulated example....
n<-400;sig2<-4
x0 <- runif(n, 0, 1);x1 <- runif(n, 0, 1)
x2 <- runif(n, 0, 1);x3 <- runif(n, 0, 1)
pi <- asin(1) * 2
f <- 2 * sin(pi * x0)
f <- f + exp(2 * x1) - 3.75887
f <- f + 0.2 * x2^11 * (10 * (1 - x2))^6 + 10 * (10 * x2)^3 *
(1 -x2)^10 - 1.396
e <- rnorm(n, 0, sqrt(abs(sig2)))
y <- f + e
# fit GAM....
b<-gam(y~s(x0)+s(x1)+s(x2)+s(x3))
# produce a plot just for second term
plot(b,select=2)
# and add partial residuals...
d<-predict(b,type="terms")
points(x1,b$residuals+d[3,],col=2)
Thanks also for the previous suggestions - I'll add them to the list, but
I doubt any will be in version 0.9, which is a bit too near to
completion now.
Simon
_____________________________________________________________________
> Simon Wood simon at stats.gla.ac.uk www.stats.gla.ac.uk/~simon/
>> Department of Statistics, University of Glasgow, Glasgow, G12 8QQ
>>> Direct telephone: (0)141 330 4530 Fax: (0)141 330 4814