On 4 May 2004, Jari Oksanen wrote:
On Tue, 2004-05-04 at 09:34, Prof Brian Ripley wrote:
Yes, but princomp is the recommended way, not prcomp.
But the documentation seems to recommend prcomp:
For numerical accuracy, but not for flexibility.
?prcomp:
The calculation is
On Tue, 2004-05-04 at 09:56, Prof Brian Ripley wrote:
On 4 May 2004, Jari Oksanen wrote:
On Tue, 2004-05-04 at 09:34, Prof Brian Ripley wrote:
Yes, but princomp is the recommended way, not prcomp.
But the documentation seems to recommend prcomp:
For numerical accuracy, but
[EMAIL PROTECTED] wrote:
Hello R-help
I use R program on linux.
and when I would like to quick R, then I type q()
after than has question Save workspace image? [y/n/c]:
when I ans y , why not to ask about name of file.
It saves the file .RData in the current working directory (getwd()
tells you
See library(tseries) library(urca).
Lib tseries has cointegration test for ADF and PO, whereas the newly
added urca package has functions for Johansen VECM test.
Cheers
Manoj
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Erin Hodgess
Sent:
Hello everybody,
is there a possibility to install and use multiple versions of a R library
at the same time?
A few words regarding the background of this question:
If I change functions of an already developed package, I have to
verify complex functions in a lot of R applications. So it would
[EMAIL PROTECTED] wrote:
Hello everybody,
is there a possibility to install and use multiple versions of a R library
at the same time?
A few words regarding the background of this question:
If I change functions of an already developed package, I have to
verify complex functions in a lot of R
Hello!
I need to test the adjustment of a (Negative) Exponential Distribution to a
dataset. The parameter of the distribution is unknown. What is the
appropriate test to do? I've tried the ks.test, although I think this isn't
the appropriate one, as I don't know the parameter.
Can anybody help
Hi. I want to use R with very large files, a couple hundred megabytes,
but R crashes every time that I try.
Reading help files seems to indicate that R ought to manage its memory
itself. I know I have enough memory since stata handles these files
perfectly well. I have a mac running OS 10.3
Does anyone know why this is happening?
diff.prop[1:5]
1 2 3 4 5
-0.6323988 -0.5226586 -0.5605096 -0.6656347 -0.6011561
ts(diff.prop, start = c(1997, 11), frequency = 1)
Time Series:
Start = 2007
End = 2125
Frequency = 1
[snip]
diff.prop is a
Ko-Kang Kevin Wang wrote:
Does anyone know why this is happening?
diff.prop[1:5]
1 2 3 4 5
-0.6323988 -0.5226586 -0.5605096 -0.6656347 -0.6011561
ts(diff.prop, start = c(1997, 11), frequency = 1)
I think you mean
ts(diff.prop, start = c(1997, 11),
Hi,
- Original Message -
From: Uwe Ligges [EMAIL PROTECTED]
I think you mean
ts(diff.prop, start = c(1997, 11), frequency = 12)
Whoops, indeed..thanks! That was a stupid question *_*
kevin Wang
__
[EMAIL PROTECTED] mailing list
Janet Rosenbaum wrote:
Hi. I want to use R with very large files, a couple hundred megabytes,
but R crashes every time that I try.
Reading help files seems to indicate that R ought to manage its memory
itself. I know I have enough memory since stata handles these files
perfectly well. I have a
hello Kevin,
On Tue, 2004-05-04 at 19:01, Ko-Kang Kevin Wang wrote:
Does anyone know why this is happening?
diff.prop[1:5]
1 2 3 4 5
-0.6323988 -0.5226586 -0.5605096 -0.6656347 -0.6011561
ts(diff.prop, start = c(1997, 11), frequency = 1)
On Tue, 4 May 2004, Janet Rosenbaum wrote:
Hi. I want to use R with very large files, a couple hundred megabytes,
but R crashes every time that I try.
If it actually crashes there is a bug, but I suspect that it stops with an
error message -- please do read the posting guide and tell us
Thank you very much, Mr Bibo,
btw... indeed. i'm very happy after read your answer on 22 Apr.
Best Regards,
--
Unung Istopo Hartanto
ENCIETY Business Consult
Research, Consulting and Training
Jl. Manyar Tirtoyoso Utara V/7 Surabaya
Dear all,
I was trying to see how the function 'confint' is defined. Doing
confint
function (object, parm, level = 0.95, ...)
UseMethod(confint)
environment: namespace:stats
does not really enlighten me. How can I get to see the implementation (I guess it
should be possible according to the
confint is generic so it does nothing but dispatch appropriate
methods. If you do methods(confint), you'll see
methods(confint)
[1] confint.lm*
Non-visible functions are asterisked
Typing confint.lm will give you an error because the function is not
exported by the stats package
You _are_ looking at the definition of confint(), which is a generic. What
you're probably interested in are the methods, which you can find by:
methods(confint)
[1] confint.lm*
Non-visible functions are asterisked
getAnywhere(confint.lm)
A single object matching 'confint.lm' was found
Dear all,
I have a data frame with different numbers of NA´s in each column, e.g.:
x y
1 2
NA 3
NA 4
4 NA
1 5
NA NA
I now want to do a linear regression on y~x with all the NA´s removed.
The problem now is that is.na(x) (and is.na(y) obviously gives vectors
with different
By (`factory') default that's done for you automagically, because
options(na.action) is `na.omit'.
If you really want to do it `by hand', and have the data in a data frame,
you can use something like:
lm(y ~ x, df[complete.cases(df),])
HTH,
Andy
From: Christoph Scherber
Dear all,
I have
actually, the situation is much more complicated. I am producing
multiple graphs within a for loop. For some strange reason, the
plotting routine always stops once lm(y~x) encounters more than one
missing value (I have marked the important bit with ***):
par(mfrow=c(5,5))
1. If your code actually runs, you should upgrade R, and quit using `_' for
assignment... 8-)
2. You seem to have an extraneous `]' after the na.exclude. Could that be
the problem?
Andy
From: Christoph Scherber
actually, the situation is much more complicated. I am producing
multiple
On Mon, 3 May 2004, Francis Dimzon wrote:
Hi all,
Please help on this. We will be teaching epidemiology using opensource
software. What are R built-in functions or functions in available packages
that are capable of doing these:
a) Logistic regression (glm?)
glm
b) Conditional
On Tue, 4 May 2004, Liaw, Andy wrote:
1. If your code actually runs, you should upgrade R, and quit using `_' for
assignment... 8-)
2. You seem to have an extraneous `]' after the na.exclude. Could that be
the problem?
More seriously, the for() loop over k will mess up the value of k that
it all works fine (the regression lines fit correctly to the data) as
long as there are not both missing values in j and k.
What suggestions would you have for this? Or, more precisely, how would
you create multiple graphs from subsequent columns of a data.frame?
Thomas Lumley wrote:
On Tue,
1. There should have been warning or error when using _ as it is
depreceated. Use - instead.
2. There is an extra ]
3. Could it be that after removing all the cases with NA, you do not
have sufficient observations. Example :
j - c(NA, 2, NA, 4, NA)
k - c(1, NA, 3, NA, 5)
Dear list,
(also sent to Roger Bivand, but perhaps somebody of you can help me also)
I am trying to use package spdep for fitting an SAR model with errorsarlm.
However, I am not sure how to make a valid nb object out of my
neighborhood. As far as I have seen, there is no documentation for
Does anyone have a good (and specific) reference for an explanation for
the calculation of degrees of freedom in treatment contrasts? I checked
the indexes of Venables and Ripley 2002, Crawley 2002, and Neter et al.
(Applied Linear Statistical Models, 4th ed.), as well as the lm code. I
would
Hi,
is there any function to fit a spatial CAR model or to compute the
iterated Papadakis method as in Sec. 5.2/5.3 of Ripley (1981) Spatial
Statistics? errorsarlm in spdep seems to be the SAR fit, or are there
alternatives for that? (Only methods based on neighborhood lists are of
interest here;
Hi folks,
I have a vaiable Y and an associated factor Z at several (13)
levels.
boxplot(Y~Z)
produces a nice array of boxplots, one for each level of Z,
and each duly labaelled with its level of Z.
I would like to superpose on each boxplot the actual data
points which it represents, i.e. do
Try:
y = rnorm(50)
z = factor(rep(1:5, each=10))
boxplot(y~z, horizontal=TRUE)
stripchart(y~z, add=TRUE)
HTH,
Andy
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of
[EMAIL PROTECTED]
Sent: Tuesday, May 04, 2004 10:48 AM
To: [EMAIL PROTECTED]
Hi I got two questions about the nnet function in R. I would be thankful to
have an answer.
1) Does the function intrinsically normalize the X and Y matrices before
the training, or normalization should be
done by the user.
2) I need to understand the $wts matrix. I do imagine that it is a
What about:
y-rnorm(100);z-sample(1:7,100,T);boxplot(y~z);points(y~z)
Peter Wolf
Ted Harding wrote:
Hi folks,
I have a vaiable Y and an associated factor Z at several (13)
levels.
boxplot(Y~Z)
produces a nice array of boxplots, one for each level of Z,
and each duly labaelled with its level of Z.
Hello
I just upgraded my version of R to 1.9.0 for Windows (2000 and XP)
When trying to run the library Hmisc I get the following error:
Error in testRversion(descfields) : This package has not been installed
properly
See the Note in ?library
Till now, I had no problem with other libraries...
Dear expert,
I have two coefficients and covariance matrix.
My objective is sampling 1000 times from the mean and covariance matrix.
In order to get that, what kind of commend should I use?
If you do not mind, could you tell me the comment in detail about
parameter used in that
On Tue, 4 May 2004, Tarca Adi Laurentiu wrote:
Hi I got two questions about the nnet function in R. I would be thankful to
have an answer.
I don't think you have consulted the book this R code supports: please do
so.
1) Does the function intrinsically normalize the X and Y matrices before
On Tue, 4 May 2004, Christoph Scherber wrote:
it all works fine (the regression lines fit correctly to the data) as
long as there are not both missing values in j and k.
That's very strange. The lines
for (k in 1:length(foranalysis[93:174,i]))
On Tue, 04 May 2004 11:21:37 -0400 Sung Kim wrote:
Dear expert,
I have two coefficients and covariance matrix.
My objective is sampling 1000 times from the mean and covariance
matrix.
In order to get that, what kind of commend should I use?
If you do not mind, could you tell me the
The MASS library has the function mvrnorm() which you should be able
to use.
-roger
Sung Kim wrote:
Dear expert,
I have two coefficients and covariance matrix.
My objective is sampling 1000 times from the mean and covariance matrix.
In order to get that, what kind of commend should I
It seems to me that the problem happens to the graphic window that is generated
immediately after the R window is minimized.
Minghua
From: [EMAIL PROTECTED] on behalf of Yao, Minghua
Sent: Fri 4/30/2004 4:12 PM
To: Prof Brian Ripley
Cc: R Help
Subject: RE:
You have been asked for a reproducible set of conditions -- this is the
first time `minimized' has been mentioned. If you can find a completely
reproducible set of actions please file a bug report (after reading the
FAQ section carefully).
We cannot help you otherwise, and don't want to spend
On Tue, 4 May 2004, Christian Hennig wrote:
Dear list,
(also sent to Roger Bivand, but perhaps somebody of you can help me also)
I am trying to use package spdep for fitting an SAR model with errorsarlm.
However, I am not sure how to make a valid nb object out of my
neighborhood. As far
On Tue, 4 May 2004, Christian Hennig wrote:
Hi,
is there any function to fit a spatial CAR model or to compute the
iterated Papadakis method as in Sec. 5.2/5.3 of Ripley (1981) Spatial
Statistics? errorsarlm in spdep seems to be the SAR fit, or are there
alternatives for that? (Only
Great!!! This works, many thanks!
**
using lsfit(x,y) instead of lm(y~x) produces a perfectly correct output.
***
Thomas Lumley wrote:
On Tue, 4 May 2004, Christoph Scherber wrote:
it all works fine (the regression lines fit correctly to the data) as
long as there are
Thanks, Andy, and Peter Wolf, for very prompt replies!
On 04-May-04 Liaw, Andy wrote:
Try:
y = rnorm(50)
z = factor(rep(1:5, each=10))
boxplot(y~z, horizontal=TRUE)
stripchart(y~z, add=TRUE)
Actually the other way up works the way I want. Details:
boxplot(Y~Z)
Anne Piotet wrote:
Hello
I just upgraded my version of R to 1.9.0 for Windows (2000 and XP)
When trying to run the library Hmisc I get the following error:
Error in testRversion(descfields) : This package has not been installed
properly
See the Note in ?library
Till now, I had no problem with
My code is over 700 lines. That is why I didn't send it. I am sorry I did not tell you
this.
See this code,
for(i in 1:20){
windows()
par(cex = 0.75)
plot(1:10)
}
if the RGui window is minimized immediately (by clicking the minimize button on the
upper right corner) after the code
Why did you minize the RGui frame? Since it is minmized, there is no room
for any windows, as I believe they are now sized to fit within the frame:
see the CHANGES file which says
Changed windows() so that new windows fit within the MDI client
area.
So just don't minimize the MDI frame.
while within a panel function for xyplot, how can I
find out the values of (effectively) xlim and
ylim -- no matter whether they have been set
explicitly or chosen by Lattice itself?
...
Not surprising, since there's no documented way to do this.
You could
try something along these
Yao, Minghua wrote:
My code is over 700 lines. That is why I didn't send it. I am sorry I did not tell you this.
See this code,
for(i in 1:20){
windows()
par(cex = 0.75)
plot(1:10)
}
if the RGui window is minimized immediately (by clicking the minimize button on the upper right
The thing is, it is *terms* that have degrees of freedom, and that does
not depend on the contrasts used except in rather exceptional
circumstances (when you set them with C() being one).
And the number of df assigned to a term depends on what went before, as
well as the data (since you can
Could someone remind me how to control the libraries and the search
order used by 'R CMD INSTALL'? I need to override the usual order to
resolve a conflict on the old SGI I'm working with. There must be
something I can do with configure-args, right? And what is the syntax
for using multiple
Douglas Bates [EMAIL PROTECTED] writes:
Deborah Swayne [EMAIL PROTECTED] writes:
Could someone remind me how to control the libraries and the search
order used by 'R CMD INSTALL'? I need to override the usual order to
resolve a conflict on the old SGI I'm working with. There must be
Hi
Lutz Prechelt wrote:
while within a panel function for xyplot, how can I
find out the values of (effectively) xlim and
ylim -- no matter whether they have been set
explicitly or chosen by Lattice itself?
...
Not surprising, since there's no documented way to do this.
You could
try something
Hi, there.
I am trying to read multiple files into R, but I got following message
Error in file(file, r): All connections are in use.
I clean up memory everytime I read in one file. Do i have to somehow
release file connection everytime i read in one??
Thanks.
Lei
Department of Chemsitry
On Tue, 4 May 2004, Lei Jiang wrote:
I am trying to read multiple files into R, but I got following message
Error in file(file, r): All connections are in use.
I clean up memory everytime I read in one file. Do i have to somehow
release file connection everytime i read in one??
No, but
I am currently using a window based system to run R. I need to have a
C++ program to call some functions in R. With what I have read, the
DCOM R server seems to have a way to interface R with C++. However with
the readme.txt file that is with download, It gives example from VB and
python, but
Hi all,
I am wondering if someone has a good reference for
scaling variables when running nonlinear optimization.
I would apreciate it if someone can direct me to a
book or lecture notes on the web. I need to know the
general intuition about doing this.
Thank You
Gabriel.
If you open a connection within a function it is often a good idea to
set an on.exit expression that will close the connection. This will be
called even if your function terminates via stop(). Here is an example:
con - file(foo)
open(con)
on.exit(close(con), add=TRUE)
HTH,
Vadim
Is there a function that takes a string and creates and assigns a
variable with that name? Could someone point me in the right direction?
Thnx
W
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
PLEASE do read the
On Tue, 4 May 2004 [EMAIL PROTECTED] wrote:
Is there a function that takes a string and creates and assigns a
^^
variable with that name? Could someone point me in the right direction?
?assign
--
Brian D. Ripley,
assign().
-roger
[EMAIL PROTECTED] wrote:
Is there a function that takes a string and creates and assigns a
variable with that name? Could someone point me in the right direction?
Thnx
W
__
[EMAIL PROTECTED] mailing list
Dear all,
I am using panel graphics to do a stripplot of a variable versus a shingle
and putting a loess curve on the stripplot. I want the data jittered, but I
can't seem to get the panel function to work. This jitter's the data, but
of course doesn't give me the loess:
stripplot((g[,3]) ~
Have you tried ?assign? That works, as does its converse get.
hope this helps. spencer graves
[EMAIL PROTECTED] wrote:
Is there a function that takes a string and creates and assigns a
variable with that name? Could someone point me in the right direction?
Thnx
W
On Tuesday 04 May 2004 05:05 pm, Sean Davis wrote:
Dear all,
I am using panel graphics to do a stripplot of a variable versus a shingle
and putting a loess curve on the stripplot. I want the data jittered, but
I can't seem to get the panel function to work. This jitter's the data,
but
of
I'm attempting to use xyplot() within a for() loop to plot the relationship
between a DV and a series of predictor variables, split by 2 conditioning
variables. However, xyplot() does not seem to be recognized within the for()
loop; I don't receive any error message, but nothing is plotted and
Wondered about the best way to control for input variables that have a
large number of levels in 'rpart' models. I understand the algorithm
searches through all possible splits (2^(k-1) for k levels) and so
variables with more levels are more prone to be good spliters... so I'm
looking for ways
Dave,
I think inside the loop you have to explicitly print a trellis object,
i.e. say
print(yplot(tmp.df$y.tmp ~ tmp.df[,i]))
If you read the help page for xyplot, look under Value.
Hope this helps,
Andy
__
Andy Jaworski
518-1-01
Process Laboratory
3M
Thanks to Andy and Bert for setting me straight! Explicitly printing the xyplot
command takes care of the issue. Just didn't dig quite far enough into the
documentation.
cheers, Dave
[EMAIL PROTECTED] wrote:
Dave,
I think inside the loop you have to explicitly print a trellis object,
i.e.
AFAIK rpart does not have built-in facility for adjusting bias in split
selection. One possibility is to define your own splitting criterion that
does the adjustment is some fashion. I believe the current version of rpart
allows you to define custom splitting criterion, but I have not tried it
I'm looking for a function that returns the time at which a permanently stored version
of a dataset (object) was last modified, just like dataset.date in S-Plus. Any
suggestions?
-
[[alternative HTML version deleted]]
On Tue, 4 May 2004 17:25:00 +0100 (BST), Prof Brian Ripley
[EMAIL PROTECTED] wrote:
Why did you minize the RGui frame? Since it is minmized, there is no room
for any windows, as I believe they are now sized to fit within the frame:
see the CHANGES file which says
Changed windows() so that
Hi, there,
Suppose I have two vector say x=c(1 2 3 4 5) and y=(2
3 6 7). Then I want to combine these two vector
together and get z=c(1 2 3 4 5 6 7) with 2 and 3 only
appear once. I want to extend this one to a general
case(say more than 100 elements in x and y and each
time I don't know which
Try
x - c(1,2,3,4,5)
y - c(2,3,6,7)
z - c(x,y)[!duplicated(c(x,y))]
HTH,
Jules
Mike wrote:
Hi, there,
Suppose I have two vector say x=c(1 2 3 4 5) and y=(2
3 6 7). Then I want to combine these two vector
together and get z=c(1 2 3 4 5 6 7) with 2 and 3 only
appear once. I want to
If it actually crashes there is a bug, but I suspect that it stops with an
error message -- please do read the posting guide and tell us exactly what
happens.
Sorry, I hadn't realized that crash means to give an error message on
this mailing list.
To me, crash means that the computer
Hi List,
Just wondering if there is such a thing as repeated measures
regression, and if so, can R do it?
I have repeated measurements of 10 individuals over a 45 day period,
and I would like to regress their daily activity time against a daily
environmental temperature. If I do so using
What do you mean by `a permanently stored version of a dataset'?
If you mean a save()d version, use file.info() on the saved file.
R does not store objects `permanently' as S-PLUS (sic) does, so your exact
phrasing is meaningless.
On Tue, 4 May 2004, Jason Watts wrote:
I'm looking for a
Hi Neil,
-Mensaje original-
De: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] nombre de [EMAIL PROTECTED]
Enviado el: lunes, 03 de mayo de 2004 23:22
Para: [EMAIL PROTECTED]
Asunto: [R] Factor loadings and principal component plots
Hi- Can anyone tell me the command(s) to
Hi,
Can someone tell me how to use R to solve a simple LP problem like this?
Thanks!
Maximize 5X1 + 3X2
Subject to:
2X1 + X2 =40
X1 + 2X2 =50
Where
X1 = 0
X2 =0
Andy
_
MSN
__
[EMAIL
Hi,
Can someone tell me how to use R to solve a simple LP problem like this?
Thanks!
Maximize 5X1 + 3X2
Subject to:
2X1 + X2 =40
X1 + 2X2 =50
Where
X1 = 0
X2 =0
help(I.will.do.my.own.homework) is the function you're looking for.
Cheers
Jason
Well, factor loadings apply to factor analysis, not PCA, so have you
confused the two? (Lots of the literature does.)
On Mon, 3 May 2004 [EMAIL PROTECTED] wrote:
Hi- Can anyone tell me the command(s) to produce the following plots:
-Factor loadings plot for principal components
-Plot of
On Tue, 2004-05-04 at 09:34, Prof Brian Ripley wrote:
Yes, but princomp is the recommended way, not prcomp.
But the documentation seems to recommend prcomp:
?prcomp:
The calculation is done by a singular value decomposition of the
(centered and scaled) data matrix, not by using
82 matches
Mail list logo