,
self-contained, reproducible code.
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do
: Henrique Dallazuanna [mailto:[EMAIL PROTECTED]
Enviado el: martes, 24 de julio de 2007 13:36
Para: Lucia Zarauz
CC: r-help@stat.math.ethz.ch
Asunto: Re: [R] plotting gam models
see ?predict.gam
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R
-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
__
R-help@stat.math.ethz.ch mailing
/AIC/UBRE
criterion?
Yes (assuming you're not using neg bin with unknown theta). But are the models
very different?
simon
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
__
R
product penalties. So, with high enough
smoothing parameters, the term will be shrunk to zero (and hence have zero
EDF).
Simon
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
__
R
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood
selection, but bearing in mind that in that case
it's an approximation without good supporting theory,
best,
Simon
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
__
R-help
_
Receba GR�TIS as mensagens do Messenger no seu celular quando voc�
estiver offline. Conhe�a o MSN Mobile!
[[alternative HTML version deleted]]
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603
mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603
do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603
do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
Seattle, WA
__
[EMAIL PROTECTED] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603
GCV or (generalized)
AIC.
Simon
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do
Don't know if this helps, but...
gam in package mgcv will let you set up smooths that interact with factors
using the `by' variable mechanism. See ?gam.models, particularly the last
example. Prediction is supported.
Simon
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2
with
something like te(x,z) then the effect of the response could be positive or
negativedepending on the values of x and z.
Simon
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
of the covariance turns out to be 9. In Simon Wood's
book, the rank of covariance matrix is usually either 9 or 99 (pages
239-230 and 259).
Can anyone comment on why so many smooth terms have a denominator
degree of freedom involving 9. Simon Wood writes r is usually
determinted numerically, while
like GCV, AIC, confidence
interval coverage and approximate p-values for guidance, but not as the basis
for rules... modelling context has to play a part as well.
Sorry if that's all a bit vague.
Simon
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225
/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood, Mathematical Sciences, University
I'll try and get
uploaded to CRAN today.
Simon
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood
.
--
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood, Mathematical Sciences, University
? If you do
then it removes the ambiguity in the model, and makes everything a bit
easier.
best,
Simon
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
__
R-help@stat.math.ethz.ch
]]
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood, Mathematical
/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
]]
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented, minimal,
self-contained, reproducible code.
--
Simon Wood
/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html and provide commented,
minimal, self-contained, reproducible code.
--
Simon Wood, Mathematical Sciences, University of Bath, Bath, BA2 7AY UK
+44 1225 386603 www.maths.bath.ac.uk/~sw283
constrOptim only fits inequality constraints.
Is there an alternative to lead with this problem?
- Any reason not to just replace e.g. parameter 8 with minus the sum of
parameters 5, 6, and 7?
best,
Simon
- Simon Wood, Mathematical Sciences, University of Bath, Bath BA2 7AY
- +44
6.252755 0.
Xs(x0)Fx1-0.325 0.1028794 392 -0.000316 0.9997
Xs(x1)Fx1 0.3831694 0.0957323 392 4.002509 0.0001
Xs(x2)Fx1 1.4584330 0.3909237 392 3.730736 0.0002
Xs(x3)Fx1-0.0123951 0.0143162 392 -0.865809 0.3871
Correlation:
Hope that's some use.
Simon
- Simon Wood
Could anyone please tell me what to do to resolve this error message?
- Any chance you could send me some code (and associated data) that I can
cut and paste in order to chase this up? Whatever's wrong here, `gam'
should probably pick it up before things get this far, but I can't tell
what's
matrix.
Perhaps this could be developed into a spline smooth method
for model.matrix and included in R.
On 6/30/06, Simon Wood [EMAIL PROTECTED] wrote:
smooth.matrix = function(x, df){
n = length(x);
A = matrix(0, n, n);
for(i in 1:n){
y = rep(0, n); y[i]=1;
yi = predict
smooth.matrix = function(x, df){
n = length(x);
A = matrix(0, n, n);
for(i in 1:n){
y = rep(0, n); y[i]=1;
yi = predict(smooth.spline(x, y, df=df),x)$y;
A[,i]= yi;
}
(A+t(A))/2;
}
- Simon Wood, Mathematical Sciences, University of Bath, Bath BA2 7AY
to the number of distinct
points, or fewer.
- Finally, for speed reasons, I'd use the cr basis (see ?s) if doing
this.
best,
Simon
- Simon Wood, Mathematical Sciences, University of Bath, Bath BA2 7AY
- +44 (0)1225 386603 www.maths.bath.ac.uk/~sw283/
Thanks
Savrina
*mgcv
Can you give a bit more information on exactly what you want to compare?
(maybe give example models). There are ways of comparing curves, but it is
a bit context dependent.
- Simon Wood, Mathematical Sciences, University of Bath, Bath BA2 7AY
- +44 (0)1225 386603
should ignore the reported r^2.
best,
Simon
- Simon Wood, Mathematical Sciences, University of Bath, Bath BA2 7AY
- +44 (0)1225 386603 www.maths.bath.ac.uk/~sw283/
On Tue, 6 Jun 2006, Highland Statistics Ltd. wrote:
Hello,
Why would I get an error message
## trapezoidal weights
sum(w*f) ## integral
## ... same again with standard error...
Xf - predict.gam(m,pd,type=lpmatrix)
t(w)%*%Xf%*%coef(m) ## integral
sqrt(t(w)%*%Xf%*%m$Vp%*%t(Xf)%*%w) ## its standard error
best,
Simon
- Simon Wood, Mathematical Sciences, University of Bath, Bath BA2 7AY
robust' is not roust enough in this case :-)]
Simon
- Simon Wood, Mathematical Sciences, University of Bath, Bath BA2 7AY
- +44 (0)1225 386603 www.maths.bath.ac.uk/~sw283/
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch
isn't it? All the non-zero eigenvalues are the same for this
matrix, so the eigenvectors can't be uniquely defined, can they?
best,
Simon
- Simon Wood, Mathematical Sciences, University of Bath, Bath BA2 7AY
- +44 (0)1225 386603 www.maths.bath.ac.uk/~sw283/
Andy
PS. My
- Simon Wood, Mathematical Sciences, University of Bath, Bath BA2 7AY
- +44 (0)1225 386603 www.maths.bath.ac.uk/~sw283/
On Thu, 23 Mar 2006, Bliese, Paul D LTC USAMH wrote:
Sorry if this is an obvious question...
I'm estimating a simple binomial generalized additive
mgcv::pcls will do this, but there are other packages for quadratic
programming as well. Simon
On Tue, 7 Mar 2006, Domenico Vistocco wrote:
Is there a function in R for constrained linear least squares?
I used the matlab function LSQLIN: my aim is to obtain
non-negative regression
Hi Denis,
Your first plot is of f(x) against x where \sum_i f(x_i) = 0 (x_i are
observed x's).
Your second plot is of \exp(\alpha + f(x)) against x where
\sum_i f(x_i)=0, and \alpha is an intercept parameter.
So the zero line on the first plot, corresponds to the \exp(\alpha) line
on the second
There's a periodic cubic spline smoother built into package mgcv's gam
function (although it happens not to use a B-spline basis). This can be
used in tensor product smooth surfaces. e.g.
gam(y~te(x,z,bs=c(cc,cc)))
best,
Simon
Hi..,
is there any funcrion in R to fit a periodic B-spline
I'm new to both R and to this list and would like to get
advice on how to build generalized additive models in R.
Based on the description of gam, which I found on the R
website, I specified the following model:
model1-gam(ST~s(MOWST1),family=binomial,data=strikes.S),
in which ST is my
Please send R and mgcv version numbers, as I can't replicate this
problem. best, Simon
Hello, I'm a Korean researcher who have been started to learn the R
package.
I want to make gam model and AIC value of the model to compare several
models.
I did the GAM model, but
In this case the models being compared are really identical, and the
P-value is meaningless numerical noise.
If your main focus is hypothesis testing and you really need near exact
p-values, then do this sort of testing using unpenalized models. i.e.
don't have mgcv::gam estimate the EDF of the
Looks like a bug in mgcv::summary.gam when the model is strictly
parametric... I'll take a look and fix it. thanks, Simon
In my original message I mentioned a gam fit that turns out to be a
linear fit. By curiosity I analysed it with a linear predictor only
with mgcv package, and then as a
On Tue, 20 Sep 2005, Yves Magliulo wrote:
hi,
i'm using gam() function from package mgcv.
if G is my gam object, then
SG=summary(G)
Formula:
y ~ +s(x0, k = 5) + s(x1) + s(x2, k = 3)
Parametric coefficients:
Estimate std. err.t ratioPr(|t|)
(Intercept) 3.462e+07
i'm using gam() function from package mgcv with default option (edf
estimated by GCV).
G=gam(y ~ s(x0, k = 5) + s(x1) + s(x2, k = 3))
SG=summary(G)
Formula:
y ~ +s(x0, k = 5) + s(x1) + s(x2, k = 3)
Parametric coefficients:
Estimate std. err.t ratioPr(|t|)
estimates etc. efficiently, for any
quantities derived from a fitted gam model are provided in ?predict.gam.
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk/~simon/
Department of Statistics, University of Glasgow
Hello. I want to fit a smoother spline (or an equivalent local
regression method) to a series of data in which the initial value of the
1st derivative (slope) is constrained to a specific value. Is it
possible to do this? If so, how?
- you should be able to modify the example in the help
])-exp(pred[2])
_
Simon Wood [EMAIL PROTECTED]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
starting values is likely to help here (the starting
values won't make any E(y)=0, after all).
best,
Simon
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk/~simon/
Department of Statistics, University of Glasgow
Do you ultimately need the eps files themselves with embedded fonts, or
is that you need to include them in a document that that has all fonts
embedded?
If it's the latter then you may find:
http://mpa.itc.it/markus/highres_pdf.html
useful. The trick seems to be to substitute the standard
stats:::kruskal.test.default
On Mon, 17 Jan 2005 [EMAIL PROTECTED] wrote:
I am using R 2.0.2 on a WinXP
I am trying to get the code of the Kruskal-Wallis test but
kruskal.test
function (x, ...)
UseMethod(kruskal.test)
environment: namespace:stats
ls(3)
[1] acf
the MASS library,
and a third is to use the quasi family.
Simon
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk/~simon/
Department of Statistics, University of Glasgow, Glasgow, G12 8QQ
Direct telephone: (0)141
summary.gam and anova.gam in package mgcv will report standard errors and
p-values for parametric terms, as well as smooth terms, for a gam fitted
by function gam from package mgcv.
Simon
I am new to R. I'm using the function GAM and wanted to get standard errors
and p-values for the
I am analyzing particulate matter data (PM10) on a small data set (147
observations). I fitted a semi-parametric model and am worried about
overfitting. How can one check for model fit in GAM?
- Keeping a random subset of the data as a validation set, fitting
to the remaining data and then
limit on the range
of degrees of freedom considered).
Package gss also has routines for fitting GAMs where the choise of df is
fully automatic.
best,
Simon
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk/~simon
in your models
then mgcv is probably worth a try (but I would say that). If you want to
use local regression smoothers and/or prefer the stepwise selection
approach then package gam is for you.
Simon
_
Simon Wood [EMAIL PROTECTED
_
Simon Wood [EMAIL PROTECTED]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
How I can compute in R the orthogonal complement of one matrix?
use the qr decomposition. For example:
A-matrix(rnorm(40),10,4)
B - t(qr.Q(qr(A),complete=TRUE)[,5:10])
B%*%A
best,
Simon
If A (n x m ) matrix of full column rank (nm), its orthogonal complement is
denoted by A_ .
A_
ld: warning -L: directory name (/usr/local/lib/gcc/powerpc-apple-darwin6.8/3.4.2)
does not exist
ld: warning -L: directory name
(/usr/local/lib/gcc/powerpc-apple-darwin6.8/3.4.2/../../..) does not exist
ld: can't locate file for: -lfrtbegin
make: *** [mgcv.so] Error 1
ERROR:
,
Simon
_
Simon Wood [EMAIL PROTECTED]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
How can I obtain AIC index when my model is a GAM?
Thanks
um - gam(y~s(x))
AIC(um)
- I think this works for packages mgcv (1.1) and gam.
best,
Simon
__
[EMAIL PROTECTED] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the
of the basis functions of the smooths.
best,
Simon
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk/~simon/
Department of Statistics, University of Glasgow, Glasgow, G12 8QQ
Direct telephone: (0)141 330 4530
.
Simon
_
Simon Wood [EMAIL PROTECTED]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
.
the purpose is to access to equation of smooths terms in order to have
the equation of my additive model.
best,
Simon
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk/~simon/
Department of Statistics, University
Warning in eval(expr, envir, enclos) : non-integer #successes in a
binomial glm!
- one way of specifying a logistic regression model is to supply the
observed proportion of sucesses as the response variable (e.g. y) and the
binomial n as the weights. The warning is complaining that y/n is
Hi Mark,
(2) Is there a way to tell lme (either in nlme or lme4) to just use a
specified design matrix Z for the random effects, rather than
constructing one itself from factors? Sometimes I would really like to
use my own funny-looking Z matrix (e.g. with non-integer coefficients),
and even
It might be worth looking at:
http://www.ruwpa.st-and.ac.uk/estimating.abundance/
best,
Simon
On Thu, 29 Apr 2004, Villirillo wrote:
Hello, I'm a final-year student in statistics and I deal with as subject of thesis
rare and elusive populations. I want make a simulation, in which I want
Golub and van Loan (1996) will probably tell you what
to do.
Simon
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk/~simon/
Department of Statistics, University of Glasgow, Glasgow, G12 8QQ
Direct telephone: (0)141
From mgcv 1.0 you can add your own smoothers for use with gam, but only if
they can be represented using basis functions and a quadratic penalty: so
P-splines are OK, but loess is not, for example.
Simon
Loader's book is referring to the gam() function in S-plus (or S from Bell
Labs), not the
of mgcv.
2. There's likely to be the odd teething problem - please let me know
about them so they can get fixed.
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk/~simon/
Department of Statistics, University of Glasgow
I want to extract the first non-zero digit of any vector, as for example
from a-runif(100,0,1).
a[min((1:length(a))[a!=0])]
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk/~simon/
Department of Statistics
I think pcls will do what you want. You'll need to explicitly set up the
constraint matrix, since pcls is designed to deal with general linear
inequality constraints (i.e. it will do more than just non-negativity).
Also the penalty matrix/matrices for pcls would be t(L)%*%L, I think.
btw, there's
Maybe try Mark Bravingtons's debug package? (see article in last R news)
is there a more convenient way to debug R code than the built in debug()
function? (so that one can set breakpoints, step in and out of function
calls,...). I read the section on debugging compiled code in the manual
.
_
Simon Wood [EMAIL PROTECTED]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
__
[EMAIL
.
_
Simon Wood [EMAIL PROTECTED]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
__
[EMAIL PROTECTED] mailing
of Newton's method)? There's an R
library for quadratic programming
Simon
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk/~simon/
Department of Statistics, University of Glasgow, Glasgow, G12 8QQ
Direct telephone: (0
wait to see
what the referees say though!)
Simon
ps. mgcv 0.9 out now! (changes list linked to my www page)
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk/~simon/
Department of Statistics, University of Glasgow
/usr/bin/ld: cannot find -lf77blas
- this is the problem, the linker can't find the basic linear algebra
system library on your machine (I'm surprised R can be built without
this). I think you may need to install the atlas package, but am not sure:
hopefully someone else will know...
Simon
mgcv 0.9 will handle missing values properly (provided you are happy that
dropping them is 'proper'). There is a pre-release version at:
www.stats.gla.ac.uk/~simon/simon/mgcv.html
(it is a pre-release version, so there will be bugs, reports of which
gratefully received!)
simon
Thank you for
?
- By default, persp picks up the first two covariates in your model. If
you want to plot against other variables you need to tell persp this...
see ?persp.gam.
best,
Simon
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk
] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk/~simon/
Department of Statistics, University of Glasgow, Glasgow, G12 8QQ
Direct telephone: (0)141 330
^{-T}X using solve() (assuming model is
y=Xb+e).
Simon
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk/~simon/
Department of Statistics, University of Glasgow, Glasgow, G12 8QQ
Direct telephone: (0)141 330 4530
and Van Loan, Matrix Computations (1983, section 6.4. p162 - I don't
have newer editions to hand).
Simon
_
Simon Wood [EMAIL PROTECTED]www.stats.gla.ac.uk/~simon/
Department of Statistics, University of Glasgow, Glasgow
_
Simon Wood [EMAIL PROTECTED]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
__
[EMAIL PROTECTED] mailing
I've got the R library mgcv for GAM written by Simon Wood which works well
in many instances. However, over the years I
got attached to the S+ implementation of GAM which allows loess smoothing in
more than 1 dimension as well as spline smoothing.
Has anyone ported the S+ GAM library to R
).
Simon
_
Simon Wood [EMAIL PROTECTED]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
It's the gam.predict example. Instead of pred-predict.gam(b,newd) I tried
pred-predict.gam(b).
- Ok, thanks - this is a bug I missed, I'll fix it. The results should be
unaffected, though. Simon
__
[EMAIL PROTECTED] mailing list
?
Simon
_
Simon Wood [EMAIL PROTECTED]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
8-) 2) It is very memory hungry, esp. when using the s() function: I have
8-) 192Mb with 256Mb swap (not a lot, but reasonable I'd say), and I've
8-) never had to kill R as often as when trying gam()...
8-)
8-) - do you have a very large number of data? The way mgcv works it first
Incidentally, this may well be a reason for the irritating habit of DLLs
in setting the floating point precision to 53 bits (well, the irritating
bit is not changing it back). This makes the results of computations
more nearly independent of where the numbers end up being stored.
- I suspect
.
Simon
_
Simon Wood [EMAIL PROTECTED] www.ruwpa.st-and.ac.uk/simon.html
Department of Statistics, University of Glasgow, Glasgow, G12 8QQ
Direct telephone: (0)141 330 4530 Fax: (0)141 330 4814
On Wed, 22 Jan 2003
My goal is to find a model (GAM with thin plate splines) in R.
I found the function gam in the R-library mgcv, but it just fits
one-dimensial splines.
- Unless you have an exceedingly ancient version of mgcv (0.6), it
*does* allow spline smooths of more than one variable. ?gam contains a
The default basis for smooth terms in mgcv is a truncated thin plate
spline basis, and has been since the later part of 2001. Including terms
like `s(x,z)', `s(x0,x1,x2)' in the model formula is the way to include
such terms (see help files, and examples therin).
best, Simon
Last time I worked
1 - 100 of 101 matches
Mail list logo