Brett Stansfield wrote:
-Original Message-
From: Brett Stansfield
Sent: Wednesday, 19 January 2005 4:25 p.m.
To: '[EMAIL PROTECTED]'
Subject: Document1
Doc1.doc I was trying to get R to analyse one variable of the file
Chicken Weight. when I ask
hist(data$weight)
R says x must be
Dear all,
Suppose I have a linear mixed-effects model (from the package nlme) with
nested random effects (see below); how would I present the results from
the random effects part in a publication?
Specifically, I´d like to know:
(1) What is the total variance of the random effects at each
BDR == Prof Brian Ripley [EMAIL PROTECTED]
on Tue, 1 Feb 2005 23:33:37 + (GMT) writes:
BDR That this prints as an octal escape was always the
BDR intention:
excuse me Brian, but always is not entirely correct:
Originally (say 6-8 years ago), the intention was really something
On Wed, 2 Feb 2005, Martin Maechler wrote:
BDR == Prof Brian Ripley [EMAIL PROTECTED]
on Tue, 1 Feb 2005 23:33:37 + (GMT) writes:
BDR That this prints as an octal escape was always the
BDR intention:
excuse me Brian, but always is not entirely correct:
Originally (say 6-8 years ago),
Paulo Justiniano Ribeiro Jr wrote:
One problem with distributing packages with the test sub-directory
is that this can overload the daily tests in the CRAN machines
My workaround for that is:
For the geoR package I run the tests in my machine but remove the tests
directory when submitting to
On Tue, 1 Feb 2005, Marc Schwartz wrote:
On Tue, 2005-02-01 at 18:48 -0800, [EMAIL PROTECTED]
wrote:
dear R wizards:
is it possible to use a postscript font symbol as a plot symbol?in
particular, I want to use the four postscript symbols for playing cards
(club, heart, spade, diamond) as
Berton Gunter wrote:
Duncan:
Bates and Pinheiro do show explicitly and in detail that the restricted log
likelihood depends on the parameterization: An important difference between
the likelihood function and the restricted likelihood is that the former is
invariant to one-to-one
On Tue, 1 Feb 2005, Hsiu-Khuern Tang wrote:
Is there a limit on the number of characters in an invocation like
R CMD BATCH --opt1=val1 --opt2=val2 ... --save-to=C:\very\long\string
..\R\script.R
?
Yes, but that is not a valid invocation of R.
I am running R 2.0.1 on Windows XP, and when running a
Please use a sensible subject line. In short, you need help().
Most R functions have a section called Examples in the help file. E.g.
help(plot) or even help(help). Granted this will give you only
snippets of a whole analysis but it is helpful nonetheless.
Since you have already identified the
These two links may be useful.
http://tolstoy.newcastle.edu.au/R/help/02b/2545.html
http://tolstoy.newcastle.edu.au/R/help/04/04/1574.html
Sean
On Feb 1, 2005, at 7:17 PM, Jon Hurley wrote:
Hi,
I have started looking into using R for generating graphs displayed in
a web browser and it produces
The REML loglikelihood includes a term -(1/2)logdet(X'WX) where X is the
design matrix for the fixed effects and W is the inverse covariance matrix
for the observations. Under reparametrisation, X becomes XM with M a
non-singular matrix, and the REML loglikelihood changes by logdet(M).
On Tue, 1
Has anybody tried out Rpad on WinXP? On my system it does not work
correctly.
Urs
__
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
Which version of Rpad do you use? It is under development, especially
for the local Rpad server under Windows.
Best,
Philippe
..°}))
) ) ) ) )
( ( ( ( (Prof. Philippe Grosjean
) ) ) ) )
( ( ( ( (Numerical Ecology of Aquatic Systems
)
great! many thanks, Phil
Cheers
christoph
Phil Spector wrote:
Christoph -
I think reshape is the function you're looking for:
tt - data.frame(cbind(c(1,1,1,1,1,2,2,2,3,3,3,3),
+ c(10,12,8,33,34,3,27,77,34,45,4,39), c('a', 'b', 'b', 'a', 'c', 'c', 'c',
+ 'a', 'b', 'a', 'b', 'c')))
Thank you for your reply and thanks for the 'fishing tip'. I thought,
however, that I had debugged my setup - I tested the ODBC connection
to MySQL directly from the ODBC driver setup and connected
successfully. If R, RODBC, and ODBC are all telling me 'life is
good', any tips on the next
This is an Autoresponder - If you need to to remove our software do this:
1- Go to the View menu on top of your Internet Explorer then Toolbars and
uncheck any blank line or tiny search bar
2- Go to www.tinybar.com , at the bottom of the page click on 'Reset your
search page back to MSN' -
On Wed, 2005-02-02 at 09:57 +, Prof Brian Ripley wrote:
On Tue, 1 Feb 2005, Marc Schwartz wrote:
On Tue, 2005-02-01 at 18:48 -0800, [EMAIL PROTECTED]
wrote:
dear R wizards:
is it possible to use a postscript font symbol as a plot symbol?in
particular, I want to use the four
I have data like:
a - rnorm(2)
b - rep(FALSE,2)
b[sample(1:2,15000)] - TRUE
Using Lattice graphics, I can produce two side-by-side histograms quite
easily by:
histogram(a | b)
However, I would like to produce a single histogram with two bars
within each bin, one for each group, as
Sean
If you want two bars for each bin then that sounds more like barplot() could be
used. I know you can tightly control the distance between bars and the width
of the bars, and so with a little coding you could probably use that.
Mick
-Original Message-
From:
A propos of these symbols, Henrik Bengtsson (Lund University, Sweden)
posted to this list some time ago a very useful function ``plotSymbols'',
which can be slightly modified as follows:
plotSymbols - function (fn=1) {
i - 0:255
ncol - 16
opar - par(cex.axis = 0.7, mar = c(3, 3, 3, 3)
Martin Maechler [EMAIL PROTECTED] writes:
yes. Patrick: it's really the case that recent versions of Linux
and other OSes AFAIK really behave differently : They default
to set locales based on UTF-8 whereas before, often locales
where based on iso-* (e.g. iso-8859-1 for Western Europe-like).
Thanks for you contributions. Jonnes' solution (after sorting) works fine
for my purposes but it would be useful to have a function that works for any
numeric prefix. Another case to include would be a signed numeric:
x-c(+12.3.abc, -0.12xyz)
Mike
- Original Message -
From: Peter
On Wed, 2005-02-02 at 10:03 -0400, Rolf Turner wrote:
A propos of these symbols, Henrik Bengtsson (Lund University, Sweden)
posted to this list some time ago a very useful function ``plotSymbols'',
which can be slightly modified as follows:
plotSymbols - function (fn=1) {
i - 0:255
Hello,
The MASS book (see bibtex below) is great. It covers all you need to
start with R and to become a wizaRd.
Romain
@Book{,
title = {Modern Applied Statistics with S},
author = {W. N. Venables and B. D. Ripley},
publisher = {Springer},
edition = {Fourth},
address = {New
Alex [EMAIL PROTECTED] writes:
Duncan,
I think that the problem in your comparison is locatted in the
method of estimation of fixed-effects: in REML they are not
estimated maximizing a joint likelihood function including
fixed-effects and variance- covariance components as ML does. So
Something a bit more sohpisticated than this:
a - rnorm(2)
b - rnorm(2, mean=1.5)
ah - hist(a,breaks= seq(-5,6,by=0.2),plot=FALSE)
bh - hist(b,breaks= seq(-5,6,by=0.2),plot=FALSE)
data - t(cbind(ah$counts,bh$counts))
barplot(data,beside=TRUE, space=rep(0,2*ncol(data)))
If you looking for something like
x1 - rnorm(1000, 0.4, 0.8)
x2 - rnorm(1000, 0.0, 1.0)
x3 - rnorm(1000, -1.0, 1.0)
hist(x1, width=0.33, offset=0.00, col=blue, xlim=c(-4,4),
main=Histogram of x1, x2 x3, xlab=x1 - blue, x2 - red, x3 - green)
hist(x2, width=0.33, offset=0.33, col=red,
On Wednesday 02 February 2005 07:42, Sean Davis wrote:
I have data like:
a - rnorm(2)
b - rep(FALSE,2)
b[sample(1:2,15000)] - TRUE
Using Lattice graphics, I can produce two side-by-side histograms
quite easily by:
histogram(a | b)
This should be ~a | b. That 'a | b' works is
Hi,
I was wondering if anyone might be able to help. I am trying to run R on a
remote machine, part of the model run I am attempting writes an external
file output as a png (about 48 iterations per model run). I am running R
1.9.1 on SuSe9.0, and am accessing this via ssh from a Debian machine.
Dear all,
Suppose I have a linear mixed-effects model (from the package nlme) with
nested random effects (see below); how would I present the results from
the random effects part in a publication?
Specifically, I´d like to know:
(1) What is the total variance of the random effects at each
This isn't exactly the same as your problem, but I came across access to X11
problems when running R over CGI.
I got round it by installing Xvfb (X Virtual Frame Buffer) on the server.
Mick
-Original Message-
From: [EMAIL PROTECTED] on behalf of Laura Quinn
Why do you use png? I think that yu need X11 to save a png file. why not
use a postscript?
This is what ?png says
R can be compiled without support for either or both of these devices:
this will be reported if you attempt to use them on a system where they
are not supported. They will not be
Do you know, please, why is package hier.part limited to the
maximum number of 12 variables? When is hierarchical partitioning
used for large-scale comparisons, I found this limitation very un-
usefull.
I tried to somehow split my data to less variables and computed the
hierarchical
I wasn't aware that it was possible to use postscript in the same fashion
as png, eg:
png(file,width=x,height=y,)
image(map)
text(text)
title(title)
box()
dev.off()
As there are a large number of iterations png has been working nicely
(when not working remotely!), especially as it has proven
May I take this off topic a little to seek collective wisdom (and so feel
free to reply privately).
The catalyst is Deepayan's remark:
Histograms were appropriate for drawing density estimates by
hand in the good old days, but I can imagine very few situations where I
would not prefer to
look intp ?postscript. these is nothingin your code below that you cannot
do in postscript.
to convert the images you can use convert (this is ImageMagick)
on your machine. On my debian machine it was preinstalled if not apt-get
imagemagick should do it. After this you can use convert blbla.eps
Berton Gunter gunter.berton at gene.com writes:
:
: May I take this off topic a little to seek collective wisdom (and so feel
: free to reply privately).
:
: The catalyst is Deepayan's remark:
:
: Histograms were appropriate for drawing density estimates by
: hand in the good old days, but
Aha, of course!
Thanks for your help - 10 minutes down to 5 seconds, superb.
Laura
Laura Quinn
Institute of Atmospheric Science
School of Earth and Environment
University of Leeds
Leeds
LS2 9JT
tel: +44 113 343 1596
fax: +44 113 343 6716
mail: [EMAIL PROTECTED]
On Wed, 2 Feb 2005, Jean Eid
Laura Quinn wrote:
I wasn't aware that it was possible to use postscript in the same fashion
as png, eg:
png(file,width=x,height=y,)
image(map)
text(text)
title(title)
box()
dev.off()
As there are a large number of iterations png has been working nicely
(when not working remotely!), especially as
Jesus and the rest of the R-help community:
Thanks for your help. I have been going over and over the examples in MASS
and the Pinheiro and Bates example, but cannot get my model to run correctly
with either aov or lme. Could someone give me a hand with the correct model
statement?
First a
Rug plots cannot show replicated values -- spikes at discrete values -- in
the data distribution. Quantile plots do.
-- Bert Gunter
Genentech Non-Clinical Statistics
South San Francisco, CA
The business of the statistician is to catalyze the scientific learning
process. - George E. P. Box
Am I correct that changing the parameterization should NOT change the
estimates of the variance components, because you are minimizing
essentially the same objective function over the same subspace? The only
thing that changes is the logdet(X'WX) term mentioned by I White?
Moreover, letting X
* On Wed 10:39AM, 02 Feb 2005, Prof Brian Ripley ([EMAIL PROTECTED]) wrote:
On Tue, 1 Feb 2005, Hsiu-Khuern Tang wrote:
Is there a limit on the number of characters in an invocation like
R CMD BATCH --opt1=val1 --opt2=val2 ... --save-to=C:\very\long\string
..\R\script.R
?
Yes, but
There are PP plots and QQ plots for any distribution, and I've
experimented a little (though not much) with PP plots and with QQ plots
for uniform, Student's t, chi-square and F distributions. I've found
qqnorm plots very useful, but I don't recall learning much from any
other
If you are aware of any upcoming R or S+ advanced
programming courses in bay area (San Francisco),
please let me know. Best alternative is Boston.
Regards -
Eugene
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
Spencer Graves wrote:
Am I correct that changing the parameterization should NOT change the
estimates of the variance components, because you are minimizing
essentially the same objective function over the same subspace? The only
thing that changes is the logdet(X'WX) term mentioned by I
Berton Gunter gunter.berton at gene.com writes:
:
: Rug plots cannot show replicated values -- spikes at discrete values -- in
: the data distribution. Quantile plots do.
:
One can address this, at least partly, using jitter and the example
I cited does precisely that.
Spencer Graves [EMAIL PROTECTED] writes:
Am I correct that changing the parameterization should NOT change
the estimates of the variance components, because you are minimizing
essentially the same objective function over the same subspace? The
only thing that changes is the logdet(X'WX)
Does anyone have any ideas (or even experience) regarding a
modified log transformation that would assign real finite values to
zeros and negative numbers? I encounter this routinely in a couple of
different situations:
* Physical measurements that are often lognormally distributed
Bickel and Doksum (JASA, 1981) discuss a modified version of the Box-Cox
transformation that looks like this:
y - ( sgn(y)* abs(y)^lambda -1)/lambda
and in the original Box-Cox paper there was an offset parameter that
gives
rise to some somewhat peculiar likelihood theory as in the
Try this using strsplit and table:
dates - c('29.02.1997','15.02.2001','15.02.2001','23.12.2002')
x.1 - do.call('rbind',strsplit(dates,'\\.'))
x.1
[,1] [,2] [,3]
[1,] 29 02 1997
[2,] 15 02 2001
[3,] 15 02 2001
[4,] 23 12 2002
class(x.1) - 'integer'
x.1
[,1] [,2] [,3]
[1,] 29
Dear all,
I have the following data format
cellnumberforce
1 100
1 230
1 100
1 200
1 130
1 210
2 179
2 298
2 400
2 500
2 600
On Wed, 2005-02-02 at 14:29 -0600, [EMAIL PROTECTED] wrote:
Dear all,
I have the following data format
cellnumberforce
1 100
1 230
1 100
1 200
1 130
1 210
2 179
2 298
2
On Wed, 2 Feb 2005 14:29:49 -0600 [EMAIL PROTECTED] wrote:
Dear all,
I have the following data format
cellnumberforce
1 100
1 230
1 100
1 200
1 130
1 210
2 179
2 298
2
Hi,
I have a question about how to get the residuals and estimations
of the parameters in my program.
For example,
x-c(1,2,3,4,5,6)
y-c(2.9, 1.24, 1.71, 2.989358, 1.455979, 1.4)
nls(y ~ a+sin(b*x),start=list(a=2.2,b=1.8),trace=TRUE)
I can get the estimation of a, b and residuals from the output
I have installed D COM server1.35 and can send a line
of R code and get a result from my VB (.net) program.
So I located all the R commands in a file (a.R) in
the dir path (c:\) then call VB using source as
below.
Dim RLink As StatConnector
RLink = New StatConnector
RLink.Init(R)
dim str
str
as.vector(coef(nlsobj))
as.vector(resid(nlsobj))
On Wed, 2 Feb 2005, Chung Chang wrote:
Hi,
I have a question about how to get the residuals and estimations
of the parameters in my program.
For example,
x-c(1,2,3,4,5,6)
y-c(2.9, 1.24, 1.71, 2.989358, 1.455979, 1.4)
nls(y ~
Assign the nls() output to an object and then use coef() and resid(), just
as you do with lm().
Andy
From: Chung Chang
Hi,
I have a question about how to get the residuals and estimations
of the parameters in my program.
For example,
x-c(1,2,3,4,5,6)
y-c(2.9, 1.24, 1.71, 2.989358,
Carsten Steinhoff carsten.steinhoff at stud.uni-goettingen.de writes:
:
: Hello,
:
: just another problem in R, maybe it's simple to solve for you. I didn't find
: a solution up to now, but I'm convinced that I'm not the only one who
: has/had a similar problem. Maybe there's a ready-made
Dear List:
I am having some trouble reproducing some GLS estimates using matrix
operations that I am not having with other R procedures. Here are some
sample data to see what I am doing along with all code:
mu-c(100,150,200,250)
Hi, there:
Recently, I read some papers about feature or attribute selection and
most of them are discussed in the context of supervised learning.
I knew Weka has implementation on some of them but I am wondering if
there is any package available in R which can do this kind of job.
Thanks for
Ich werde ab 2005-02-02 nicht im Büro sein. Ich kehre zurück am
2005-02-04.
Ich werde Ihre Nachricht nach meiner Rückkehr beantworten.
Ursprüngliches Thema: R-help Digest, Vol 24, Issue 2
[[alternative HTML version deleted]]
__
Hi,
Look for dprep package for wrapper based feature selction that use lda,
knn etc.
Also you can use package rfe that implements recursive feature elimination
using SVM.
-Original Message-
From: WeiWei Shi
To: R-help@stat.math.ethz.ch
Sent: 2/2/05 5:43 PM
Subject: [R] feature
__
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
I am immediately reminded of something I read which goes
A sufficiently trained statistician can read the vagaries of a Q-Q plot like a
sharman can read a chicken's entrails, with a similar recourse to scientific
principles. Interpreting Q-Q plots is more a visceral than an intellectual
Looking at the output from this and the previous response using barplot
worries me for two reasons :
a) The bars in front may obscure the bars at the back. The order of
plotting becomes important here.
b) IMHO, it is distracting and does not convey information well unless
one is willing to risk
Hi.
My VB program run a R - script located in the server
with R DCOM server. The R - script is designed to send
a query to DB through ODBC. There is NOT any problem
when I run each code from R-window interface.
However, when I call the R-script from my VB program
it stucked after calling
Gabor Grothendieck ggrothendieck at myway.com writes:
:
: Carsten Steinhoff carsten.steinhoff at stud.uni-goettingen.de writes:
:
: :
: : Hello,
: :
: : just another problem in R, maybe it's simple to solve for you. I didn't
find
: : a solution up to now, but I'm convinced that I'm not the
Hi,
I found the dprep package but I am wondering if there is a document
and some example on how to use it?
I am also curious if it can use cart or similar algorithm instead of
lda? I am also interested in finding some methods using GA in feature
selection.
thanks
Ed
On Wed, 2 Feb 2005 18:22:13
Berton Gunter wrote:
Rug plots cannot show replicated values -- spikes at discrete values -- in
the data distribution. Quantile plots do.
But you can use rug(jitter(x))
Kjetil
-- Bert Gunter
Genentech Non-Clinical Statistics
South San Francisco, CA
The business of the statistician is to
boxplot(force ~ cellnumber)
From: [EMAIL PROTECTED]
To: r-help@stat.math.ethz.ch
Subject: [R] Boxplot by factors
Date: Wed, 2 Feb 2005 14:29:49 -0600
Dear all,
I have the following data format
cellnumberforce
1 100
1 230
1 100
1 200
It is unlikely that your request will be answered faster if you post it a
second time in exactly the same way ...
Suppose I have a linear mixed-effects model (from the package
nlme) with nested random effects (see below); how would I present
the results from the random effects part in a
When I generate a special paper postscript image larger than
a4 or letter using R, I can only see one-page portion of all
image, of course.
What will be the simple solution for this? Is there any way I
can set the bounding box information on the image? Or any other
suggestions?
I often
The experimental design was suppose to consist of 4
treatments replicated 3 time, Source 1 and applied at 10 cm
and source 2 applied at 20 cm. During the construction of the
treatmetns the depths vary considerably so i can't test all my
samples based on 10 and 20 cm any more the depths are
I have been going over and over the examples in MASS
and the Pinheiro and Bates example, but cannot get my model
to run correctly with either aov or lme.
Could someone give me a hand with the correct model statement?
It would help to see some of the things you have tried already ...
75 matches
Mail list logo