Prof Brian Ripley wrote:
On Wed, 24 Nov 2004 [EMAIL PROTECTED] wrote:
On 24-Nov-04 Witold Eryk Wolski wrote:
Hi,
I want to draw a scatter plot with 1M and more points
and save it as pdf.
This makes the pdf file large.
So i tried to save the file first as png and than convert
it to pdf. This looks
PD == Peter Dalgaard [EMAIL PROTECTED]
on 24 Nov 2004 19:35:45 +0100 writes:
PD Harry Athanassiou [EMAIL PROTECTED]
PD writes:
I'm a beginner in R, and trying to fit linear models with
different intercepts per group, of the type y ~ A*x1 + B,
where x1 is a numerical
Hello,
I am using R 1.9.1 on Windows 2000 SP4. I have the following problem:
Say I have a matrix,
my.matrix
[,1] [,2] [,3]
[1,] A B C
[2,] D E F
[3,] G H I
I would like to apply an operation to this matrix which returns a list my.list
containing the following 3
Alexander Sokol [EMAIL PROTECTED] writes:
[1] A B C
[[2]]
[2] D E F
[[3]]
[3] G H I
That is, each row of the original matrix is turned into a vector and these
vectors are collected to a list. How do I do this?
split(my.matrix, row(my.matrix))
--
O__ Peter Dalgaard
my.matrix - matrix(LETTERS[1:9],3,3,byrow=TRUE)
split(my.matrix, row(my.matrix))
$1
[1] A B C
$2
[1] D E F
$3
[1] G H I
which even names the rows for you.
On Thu, 25 Nov 2004, Alexander Sokol wrote:
Hello,
I am using R 1.9.1 on Windows 2000 SP4. I have the following problem:
Say I have a matrix,
On Thu, 25 Nov 2004, Jean Coursol wrote:
The same is true in french under linux.
No, it is not the same. Windows XP does this even in the Danish locale,
and that is a problem (in Windows).
Your problem is simply that you should be using a French locale to use
French characters. You should not
I am trying, without success, to find out how to formulate correctly the
parameters of eval.
My code snippet looks like:
proutside - function(txt) {
cat(\n,txt,\n);
print(eval(parse(text = txt)))
}
vari - function(Ob) {
prininside - function(txt) {
cat(\n,txt,\n);
Christian Hoffmann [EMAIL PROTECTED] writes:
I am trying, without success, to find out how to formulate correctly
the parameters of eval.
My code snippet looks like:
proutside - function(txt) {
cat(\n,txt,\n);
print(eval(parse(text = txt)))
}
vari - function(Ob) {
On Mon, 22 Nov 2004, Prof Brian Ripley wrote:
[...]
BTW, I believe running R 2.0.x from a CD will be a lot slower than 1.9.1
because of lazy loading and frequent file accesses: that's a theoretical
issue we intend to address for 2.1.0, but not one anyone has yet commented
that it is a problem.
I
I have an openoffice spreadsheet with a column of
character strings.
Some of them contain accents.
I want to read it in R so I have saved it as a csv
file using Western Europe (ISO-8859-1) character set
(the default, I've tried other sets but it doesn't
help).
R reads it fine with
Before I receive a barrage of 'try looking in the help file' messages, I
have and to no avail. For a new user of R I would like to point out that
in order to be able to use the help files/manuals effectively one must
know the correct question and that only comes with using R!
Could someone please
Can you please tell us what locale you are working in?
This looks as if the problem might be the use of a UTF-8 locale, which R
does not currently support and which some Linux distros have made their
default. However, R does issue a warning -- so did you get one?
On Thu, 25 Nov 2004, Manuel
Apologies to the listing, the problem was with the data set and not the
code
Thanks
Michael Griffiths, Ph.D.
Chemometrician
Training, Quality and Statistics Group
LGC Limited
Queens Road
Teddington
Middlesex, TW11 0LY, UK
Tel: +44 (0)20 8943 7352
Fax: +44 (0)20 8943 2767
e-mail: [EMAIL
Hi all
I'm trying to use the function glm from the MASS package to do the
following fit.
fit - glm(FP ~ rand, data = tab, family = poisson(link = identity),
subset = rand = 1)
(FP is = 0)
but I get the following error
Error: no valid set of coefficients has been found:please supply
starting
Dear all,
in last weeks you discussed about R vs SAS.
I want to ask your opinion about a comparison between
R and SPSS. I don't know this software, but some weeks
ago I went to a presentation of this product. I found
it really user-friendly with GUI (even if I'd prefer
command line) and very
$ locale
LANG=en_GB
LC_CTYPE=en_GB
LC_NUMERIC=en_GB
LC_TIME=en_GB
LC_COLLATE=en_GB
LC_MONETARY=en_GB
LC_MESSAGES=en_GB
LC_PAPER=en_GB
LC_NAME=en_GB
LC_ADDRESS=en_GB
LC_TELEPHONE=en_GB
LC_MEASUREMENT=en_GB
LC_IDENTIFICATION=en_GB
LC_ALL=
$ locale charmap
ISO-8859-1
I have tried changing the
Hello:
I am really stuck on this problem. Why do I get an error message with
anova() when I compare these two equations?
Hope someone can help.
ANDREW
fm1 - glmmPQL(choice ~ day + stereotypy,
+random = ~ 1 | bear, data = learning, family =
Hi,
Le 25 nov. 04, à 13:15, Vito Ricci a écrit :
command line) and very usefull and simple to use in
I do not know R so much, nor SPSS.
Then I appreciate SPSS, because tools are very practical to use.
Every transformation, model analysis are easily made.
In the other hand, let me say it doesn't
Hi folks,
is it possible to read more things about R behavior in multiprocessor /
multihost environment ?
Is there any distributed computation project associated to it ?
Laurent
__
[EMAIL PROTECTED] mailing list
Hello,
I am running R 1.9.1 om Windows 2000 SP4. My problem is as follows:
Say I have a dataframe my.frame with column names A and B. I have a string,
my.string
[1] A==1 B==2
And I would like to retrieve the subset corresponding to my.string, that is,
from my.frame and my.string I would like
On Thu, 25 Nov 2004 14:09:14 +0100, Alexander Sokol
[EMAIL PROTECTED] wrote :
Hello,
I am running R 1.9.1 om Windows 2000 SP4. My problem is as follows:
Say I have a dataframe my.frame with column names A and B. I have a string,
my.string
[1] A==1 B==2
And I would like to retrieve the subset
Good morning,
I'd like to know how to superimpose to a distribution of Pearson
coefficient the Student cumulative distribution function.
Thank you of helping me.
Angela
__
[EMAIL PROTECTED] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
Hi Alexander,
you could try:
my.string - A==1 B==2
(my.frame - data.frame(A=sample(1:2, 20, TRUE), B=sample(1:2, 20,
TRUE)))
subset(my.frame, eval(parse(text=my.string)))
I hope it helps.
Best,
Dimitris
Dimitris Rizopoulos
Ph.D. Student
Biostatistical Centre
School of Public Health
Good morning,
I tried to apply the ks test to a Student distribution by ks.test(input,
pt, ncp = 0, df = 58) or ks.test(input, pt, df = 58) without success
where input contains my data and 58 is the fredoom degree number. Why?
Thank you, Angela
__
Hello,
I am using code like the following to create as simple plot...
plot(x,y,type='b')
lines(lowess(x,y),lwd=3,lty=3,col=2)
I want to add a legend which shows lines looking exactly like those used
in my plot, i.e. a thin black line with gaps taken up by circles (the
default for type='b',
Hi Terry,
If I understood your problem you would estimate trend
and seasonal (as sum of sin and cos) in a ts.
If t is time, Y is your ts, T=f(t) is trend function
of time (it could be linear, quadratic, etc. as better
is for your data), e=errors/residuals
Your model to fit will'be:
Torsten Hothorn writes:
as long as one does not use the information in the response (the class
variable, in this case) I don't think that one ends up with an
optimistically biased estimate of the error
I would be a little careful, though. The left-out sample in the
LDA-cross-validation, will
On Thu, Nov 25, 2004 at 02:11:12PM +0100, Laurent Valdes wrote:
Hi folks,
is it possible to read more things about R behavior in multiprocessor /
multihost environment ?
Is there any distributed computation project associated to it ?
Sure. I'd start with the paper 'Simple Parallel
Angela Re wrote:
Good morning,
I tried to apply the ks test to a Student distribution by ks.test(input,
pt, ncp = 0, df = 58) or ks.test(input, pt, df = 58) without success
where input contains my data and 58 is the fredoom degree number. Why?
Thank you, Angela
Sean Davis wrote:
If you simply want read all files in a given directory, you can do
something like:
fullpath = /home/andersm/tmp
filenames - dir(fullpath,pattern=*)
pair - sapply(filenames,function(x)
{read.table(paste(fullpath,'/',x,sep=))})
Slightly off-topic but it is more portable to use
Angela Re wrote:
Good morning,
I tried to apply the ks test to a Student
distribution by ks.test(input,
pt, ncp = 0, df = 58) or ks.test(input, pt, df =
58) without success
where input contains my data and 58 is the fredoom
degree number. Why?
Thank you, Angela
It runs also for me:
Hi Andy,
On 25-Nov-04 Liaw, Andy wrote:
From: [EMAIL PROTECTED]
[...]
X-round(rnorm(1e6),3);Y-round(rnorm(1e6),3)
system.time(unique(X))
[1] 0.74 0.07 0.81 0.00 0.00
system.time(unique(cbind(X,Y)))
[1] 350.81 4.56 356.54 0.00 0.00
Do you know if majority of that time is spent
Vito Ricci wrote:
Dear all,
in last weeks you discussed about R vs SAS.
I want to ask your opinion about a comparison between
R and SPSS. I don't know this software, but some weeks
ago I went to a presentation of this product. I found
it really user-friendly with GUI (even if I'd prefer
command
I'd like to search for a particular string in an SQLite database using
RSQLite, but I'm running into problems constructing the query
properly, because of embedded quotes and parens in the string.
Is there a function that escapes these for me, or some other fixup
that would let me do the queries
Dear Mike,
Pinheiro and Bates discuss a three-parameter logistic growth model in their
Mixed Effects Models in S and S-PLUS, but as far as I know there's no direct
way to fit the 3PL IRT model in R. It should be possible to fit such a model
using one of the general optimisers in R, such as nlm()
On Thu, 25 Nov 2004, Federico Gherardini wrote:
Hi all
I'm trying to use the function glm from the MASS package to do the following
It's in the stats package.
fit.
fit - glm(FP ~ rand, data = tab, family = poisson(link = identity), subset
= rand = 1)
(FP is = 0)
but I get the following error
Vito,
I use SPSS mainly for descriptive analysis (tables, graphs, factor
analysis..) and for data manipulation (you can see your data and
verify/control each step of your manipulation), mainly exploring the
analysis I need to develop in R (advanced clustering modelling,
simulations..).
SPSS huge
I have the following problem in getting the sqlSave function from the
example code in the R package RODBC to work with MySQL as ODBC server:
- a new database is created, but no data is written to it
- the example code works just fine when I use MS Access as ODBC server.
--- offending
On Thu, 25 Nov 2004, John Fox wrote:
Pinheiro and Bates discuss a three-parameter logistic growth model in their
Mixed Effects Models in S and S-PLUS, but as far as I know there's no direct
way to fit the 3PL IRT model in R. It should be possible to fit such a model
using one of the general
Frank E Harrell Jr wrote:
What worries me about SPSS is that it often results in poor statistical
practice. The defaults in dialog boxes are not very good in some cases,
and like SAS, SPSS tends to lead users to make to many assumptions
(linearity in regression being one of the key ones).
--
Single quotes in a string are escaped by putting two single quotes in
a row. E.g.,
state - mess: '' (
Regards,
--
David
Duncan Murdoch wrote:
I'd like to search for a particular string in an SQLite database using
RSQLite, but I'm running into problems constructing the query
properly,
Hello,
My name is Mrs. Jennifer Wilson i am a dying woman who have decided to donate
what i have to you/ church.I am 59 years old and i was diagnosed for cancer for
about 2 years ago,immediately after the death of my husband, who has left me
everything he worked for.
I have been touched by
I don't know if I am missing something, but isn't there also a latent
variable (trait) that must be integrated out using maybe Gauss-Hermite
which might complicate a bit the calculations? So is this possible
with `glm()'?
Best,
Dimitris
Dimitris Rizopoulos
Ph.D. Student
Biostatistical
Dear Federico:
Why do you use the identity link? That can produce situations
with an average of (-2) Poisson defects per unit, for example. That's
physical nonsense. Also, it seems essentially to be generating your
error message.
Also, have you considered the following:
fit -
Hello R-users,
I have a symmetric matrix of numerical values and I
want to obtain those values in the upper or lower
triangle of the matrix in a vector. I tried to do the
job by using two for-loops but it doens't seem to be a
clever way, and I'd like to know a more efficient code
for a large
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Duncan Murdoch
Sent: 25 November 2004 15:38
To: [EMAIL PROTECTED]
Subject: [R] Searching for a string in RSQLite
I'd like to search for a particular string in an SQLite
database using RSQLite,
Dimitris Rizopoulos [EMAIL PROTECTED] writes:
Hi Alexander,
you could try:
my.string - A==1 B==2
(my.frame - data.frame(A=sample(1:2, 20, TRUE), B=sample(1:2, 20,
TRUE)))
subset(my.frame, eval(parse(text=my.string)))
Hmm, considering the nonstandard evaluation that is going on inside
You may find dQuote() and sQuote() to be helpful, but a better
Ooops, dQuote() and sQuote() won't be of much use as they escape
quotes with quotes.
A regular expression should do the trick: gsub(', ', Hi
y'all). (Note that this looks like it has too many backslashes, but
this is just the
I'm sorry for this spam that astonishingly came through to the
mailing list.
It seems these guys have been exercising against known spam
filters and achieved more than in the past.
Also, recent versions of our spamfilter have been tuned such as
to rather produce a few false negatives {spam not
(Ted Harding) [EMAIL PROTECTED] writes:
I want to look into this a bit more systematically (I have
an idea why 'unique' may be taking longer on the array from
'cbind' than on the dataframe),
Just look inside the functions. One is pasting columns together, the
other is using a paste()
lower triangle can be obtained by
A[row(A)col(A)]
url:www.econ.uiuc.edu/~rogerRoger Koenker
email [EMAIL PROTECTED] Department of Economics
vox:217-333-4558University of Illinois
fax:217-244-6678
John wrote:
Hello R-users,
I have a symmetric matrix of numerical values and I
want to obtain those values in the upper or lower
triangle of the matrix in a vector. I tried to do the
job by using two for-loops but it doens't seem to be a
clever way, and I'd like to know a more efficient code
for a
On Thursday 25 November 2004 11:15, John wrote:
Hello R-users,
I have a symmetric matrix of numerical values and I
want to obtain those values in the upper or lower
triangle of the matrix in a vector. I tried to do the
job by using two for-loops but it doens't seem to be a
clever way, and
Dear all,
I have a null frequency histogram of pairwise associations values.
How can I put an arrow on the histogram to indicate the critical value
obtained from the null distribution? [In this case, quantile 0.05].
Thanks
--
Rogério R. Silva
MZUSP http://www.mz.usp.br
Linux User # 354364
Spencer Graves [EMAIL PROTECTED] writes:
Dear Federico: Why do you use the identity link? That can
produce situations with an average of (-2) Poisson defects per unit,
for example. That's physical nonsense.
So is _not_ using the identity link when the model is manifestly
additive on
On 25-Nov-04 John wrote:
Hello R-users,
I have a symmetric matrix of numerical values and I
want to obtain those values in the upper or lower
triangle of the matrix in a vector. I tried to do the
job by using two for-loops but it doens't seem to be a
clever way, and I'd like to know a more
Hi, Peter:
What do you do in such situations?
Sundar Dorai-Raj and I have extended glm concepts to models
driven by a sum of k independent Poissons, with the a linear model for
log(defectRate[i]) for each source (i = 1:k). To handle convergence
problems, etc., I think we need to
Is this an impossible task?
How about just problem 2 below, having one pch in one legend entry, but no
pch in the second?
On Thu, 25 Nov 2004, Dan Bolser wrote:
Hello,
I am using code like the following to create as simple plot...
plot(x,y,type='b')
lines(lowess(x,y),lwd=3,lty=3,col=2)
On 25-Nov-04 Rogerio Rosa da Silva wrote:
Dear all,
I have a null frequency histogram of _pairwise associations values.
How can I put _an arrow on the histogram to indicate the critical value
obtained from the null distribution? [In this case, quantile 0.05].
?Something like
q05 -
I am trying to upgrade to R-2.0.1 from R-1.9 on a Mac running OS X 10.3.
I have some simple packages I wrote myself that have to be reinstalled
to be recognized as valid packages. I have been using them for a while
on earlier versions of R, so didn't expect to have any problems.
I am probably
Dan Bolser wrote:
Is this an impossible task?
How about just problem 2 below, having one pch in one legend entry, but no
pch in the second?
Please be at least a little bit patient! This is not a hotline! People
are not working 24 hours a day just to answer your questions at once -
they are
Spencer Graves [EMAIL PROTECTED] writes:
Hi, Peter: What do you do in such situations? Sundar Dorai-Raj
and I have extended glm concepts to models driven by a sum of k
independent Poissons, with the a linear model for log(defectRate[i])
for each source (i = 1:k). To handle
Hi, Peter:
Thanks for the comment and reply.
I generally avoid constrained optimizers for three reasons:
1. My experience with them has included many cases where the
optimizer would stop with an error when testing parameter values that
violate the constraints. If I
On Thu, 25 Nov 2004, Uwe Ligges wrote:
Dan Bolser wrote:
Is this an impossible task?
How about just problem 2 below, having one pch in one legend entry, but no
pch in the second?
Please be at least a little bit patient! This is not a hotline! People
are not working 24 hours a day just to
Hi Everyone
Thanks to those who responded last time.
I am still having problems. I really want to find one of those
tutorials on how to use svm() so I can then get going using it myself.
Issues are which kernel to choose, how to tune the parameters. If
anyone know of a tutorial please let me
Hello:
Will someone PLEASE help me with this problem. This is the third time
I've posted it.
When I appply anova() to two equations estimated using glmmPQL, I get a
complaint,
anova(fm1, fm2)
Error in anova.lme(fm1, fm2) : Objects must inherit from classes gls,
gnls lm,lmList,
Dear r-help list members,
Is there a way to test whether an object is an S4 object? The best that I've
been able to come up with is
isS4object - function(object) !(is.null(slotNames(object)))
which assumes that an S4 object has at least one slot. I think this is safe,
but perhaps I'm
Hi everybody on this list,
Could somebody please tell me how to expand the size limit of a vector
in R?
In my simulation I get the following error message:
x=kronecker(diag(1,100),matrix(1,100,100))
Error: cannot allocate vector of size 781250 Kb
In addition: Warning message:
Reached total
As I started out using SPSS when there was no GUI (in fact, no interactive
interface at all), I automatically open up the syntax editing window when I
have to use it. It's a workable text editor, you can run all or part of the
code at will, and build up a code file in much the same way as R.
Hi. I'm a student at Simon Fraser University in British Columbia, Canada. I
can't for the life of me figure out how to plot a 3D surface (A 3D response
surface to be more specific) in R. I found your email address on a web
board, and saw someone mention wireframe(), but using the help in R yielded
On Thursday 25 November 2004 22:35, [EMAIL PROTECTED] wrote:
Hi. I'm a student at Simon Fraser University in British Columbia,
Canada. I can't for the life of me figure out how to plot a 3D
surface (A 3D response surface to be more specific) in R. I found
your email address on a web board, and
wireframe() is available in the package lattice.
--Matt
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] Behalf Of [EMAIL PROTECTED]
Sent: Thursday, November 25, 2004 20:36 PM
To: [EMAIL PROTECTED]
Subject: [R] Response Surface
Hi. I'm a student at Simon
type ?wireframe rather than wireframe()
Tom Mulholland
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]
Sent: Friday, 26 November 2004 12:36 PM
To: [EMAIL PROTECTED]
Subject: [R] Response Surface
Hi. I'm a student at Simon Fraser University in British Columbia,
For better or worse, it's holidays in the states. Very amusing for me
being in a non-Thanksgiving celebrating country.
In addition, it's not a problem. The complaint is valid. Probably no
one has coded up the right solution yet for comparison.
I can't recall if one would want those statistics
Dear R Users, (and dear Marc)
First of all many thanks for the answers to my previous questions.
I would like to barplot the mean percent change of a variate with it's
CI. Bars should start from the zero reference line to height (in
barplot2).
Is there a way to tweak barplot2, for example, to
http://www.maths.lth.se/help/R/.R/library/e1071/doc/svmdoc.pdf
regards, christian
stephenc wrote:
Hi Everyone
Thanks to those who responded last time.
I am still having problems. I really want to find one of those
tutorials on how to use svm() so I can then get going using it myself.
Issues are
On Thu, 25 Nov 2004, Spencer Graves wrote:
I generally avoid constrained optimizers for three reasons:
1. My experience with them has included many cases where the optimizer
would stop with an error when testing parameter values that violate the
constraints. If I transform the
On Fri, 26 Nov 2004, Guoqi Qian wrote:
Hi everybody on this list,
Could somebody please tell me how to expand the size limit of a vector
in R?
You must be using Windows, without telling us. The rw-FAQ tells you the
answer, as well as the help page that message refers to. It's better for
you
I didn't know how to do this but I knew it had to been asked about.
Try getS3method(barplot2,default)
Make sure you've loaded gplots. I guessed default, but I wonder how you would
find out the class if it had been something else. I guess that's something to
work on when I'm next twiddling my
79 matches
Mail list logo