Hi
In R 1.7 the following worked fine:
array(list(),c(2,5))
[,1] [,2] [,3] [,4] [,5]
[1,] NULL NULL NULL NULL NULL
[2,] NULL NULL NULL NULL NULL
now in R 1.8.1 I get the error:
Error in rep.int(data, t1) : invalid number of copies in rep
In addition: Warning message:
NAs introduced by
Gerald == Gerald Jean [EMAIL PROTECTED]
on Tue, 13 Jan 2004 12:32:43 -0500 writes:
Gerald Hello R-users,
Gerald Version 1.8.1 on a 64-bit Solaris 5.8 OS
Gerald I am trying to instal the Rcmdr package for which the tclk package is
Gerald required. Once both package
On Wed, 14 Jan 2004, W. Beldman wrote:
I'm looking for the algorithm of the solve function (base package). As I
understand the help text neither Linpack nor Lapack's ZESV is used (in the
Well, your example is not complex. By default (LINPACK=FALSE), DGESV is
used: just read the code.
O.k., Kaverforms the average of a series of (usually simulated) K-functions.
How do I apply it on non-simulated K-functions?
Deborah Renz
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
PLEASE do read the
I am trying to use prcomp and I am getting this error:
p - prcomp(xtr, retx = TRUE, center = TRUE, scale = TRUE, tol = NULL)
Error in La.svd(x, nu, nv, method) : error code 17 from Lapack routine
dgesdd
dim(xtr)
[1] 301 2439
Does it mean that the matrix is to big ?
R
I have the following function
f - function {
...
model - lm(rttx[,1] ~ rttx[,2] + 0);
summary(model);
...
}
while summary(model) shows the summary if I execute the function line by line
in the Command Line Interface, if I call f() summary is silent
how to
Hello
Is anyone else having problems receiving email from the list? No email from R
help today!
Thanks Marwan
---
Marwan Khawaja http://departments.aub.edu.lb/~mk36
__
[EMAIL
One useful way of looking at she S language, which R implements, is as a
complete programming language with some very powerful operators already
available. Why not think about putting those operators together to do the
computations that you need to do in this case? It's not like starting from
Hello,
I would like to display two groups of dots in different colors or style and
additionnaly a linear regression for all the dots in
panel plots of a Trellis graph. Actually to get in each panel the equivalent of:
plot(x[mois==3],y[mois==3],col=blue)
points(x[mois==9],y[mois==9],col=red)
I'm analizing the Argentina stock market (merv)
I download the data from yahoo
library(tseries)
Argentina - get.hist.quote(instrument=^MERV,1996-10-08,2003-11-03,
quote=Close)
merv - na.remove(log(Argentina))
I made the Augmented Dickey-Fuller test to analyse
if merv have unit root:
my situtation is that each data point is made up of p correlated 5-dimension
vectors. Those 5 dimensions are orthogonal.
Any suggestions will be appreciated!
JP
-Original Message-
From: Liaw, Andy [mailto:[EMAIL PROTECTED]
Sent: Monday, January 12, 2004 10:00 PM
To: 'Jieping'; [EMAIL
I'm analizing the Argentina stock market (merv)
I download the data from yahoo
library(tseries)
Argentina - get.hist.quote(instrument=^MERV,1996-10-08,2003-11-03,
quote=Close)
merv - na.remove(log(Argentina))
I made the Augmented Dickey-Fuller test to analyse
if merv have unit root:
Hello everybody
I'm using contour() to draw streamlines of potential flow, eg
jj - seq(from= -4, to=4,len=20)
jj - outer(jj,jj,function(x,y){x})+1i*outer(jj,jj,function(x,y){y})
f - function(x){x^2}
contour(Im(f(jj)), nlevels=44 , labels=)
How best to put arrows on the contour lines to show
Hi
On 14 Jan 2004 at 12:01, Robin Hankin wrote:
Hello everybody
I'm using contour() to draw streamlines of potential flow, eg
jj - seq(from= -4, to=4,len=20)
jj - outer(jj,jj,function(x,y){x})+1i*outer(jj,jj,function(x,y){y})
f - function(x){x^2}
contour(Im(f(jj)), nlevels=44
Hello R-users,
Version 1.8.1 on a 64-bit Solaris 5.8 OS
I am trying to instal the Rcmdr package for which the tclk package is
required. Once both package installed I issued the command:
library(tcltk)
and received the following error message
Error in firstlib(which.lib.loc, package) :
From: Patrick Giraudoux [EMAIL PROTECTED]
Hello,
I would like to display two groups of dots in different colors
or style and additionnaly a linear regression for all the dots in
panel plots of a Trellis graph. Actually to get in each panel
the equivalent of:
On Tue, 13 Jan 2004 [EMAIL PROTECTED] wrote:
Hello R-users,
Version 1.8.1 on a 64-bit Solaris 5.8 OS
I am trying to instal the Rcmdr package for which the tclk package is
required. Once both package installed I issued the command:
library(tcltk)
and received the following error
If the data somewhat resembles multivariate Gaussian, I suppose one
possibility is to construct (by hand) something like LDA, but with the
covariance matrix constrained to be block-diagonal. Just an idea.
Cheers,
Andy
From: Jieping [mailto:[EMAIL PROTECTED]
my situtation is that each data
Hi Ott,
could it be a per process limit or ulimits set?
i don't have a solaris box here so i can't remember what the appropriate
commands are...
cheers,
Sean
Ott Toomet wrote:
Hello,
I am running a preliminary data-processing job on solaris. Basically,
the program reads a large number of
Hello R-users,
same here no PM (EST) mail. I posted a message and never saw it appear in
my mail box and no other R-mail in the afternoon yesterday.
Gérald Jean
Analyste-conseil (statistiques), Actuariat
télephone: (418) 835-4900 poste (7639)
télecopieur : (418) 835-6657
Hi,
I'm trying to figure out some stastistics for non-nested models testing.
Among them:
[1] Vuong statistic (Vuong, 1989)
[2] Distribution-free test by Clarke (2003).
Did someone wrote a piece of [R] code to compute any of them?
Many thanks,
Bruno
Bruno L.
Hi,
I am trying to use the stl function in the ts package. It requires that
the data is a univariant time series at the moment my data is in a
vector. I have coerced it to a time series using
crimets - ts(crimeData)
However, this does not work.
Does anyone have any suggestions?
Cheers,
On Mon, 12 Jan 2004, Spencer Graves wrote:
Have you looked at library(survival)? Unless I misunderstand what you
want, it should be there
It isn't.
-thomas
. Further documentation is provided in Venables
and Ripley (2002) Modern Applied Statistics with W, Therneau and
Hello
I want to fit an AR model were two of the coefficients are fixed to zero
(the second and third ar-coefficients).
I used the arima function with the fixed argument but the ar3
coefficient is not set to zero:
==
arima(Y, order=c(4,0,0),
Hello all,
I'm hoping this is a simple problem.
I'm trying to do cca of my data. I have my plant data and environmental data as 2
separate files. I have 3 years of data, stacked vertically, within these files. I
want to conduct the cca for each year and am trying to create separate year
Hi there
does anyone know about a downloadable CRAN for copula functions for R?
Thank you so much for your answers.
Hanspeter
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
Dear, R experts.
I have two program codes, one is made by Splus and the other
is made by transferring from Splus code. Because nlminb function
in Splus is equivalent to optim in R, I expected to get exactly same
result. But, sometime there is too large differece (greater than 2%)
between two
Hello,
does anyone know about:
a) simulating seasonal ARIMA models? arima out of package ts can fit it,
but it does not look like it can simulates data from seasonal models
b) fitting and simulating fractional seasonal ARIMA models?
Hints will be appreciated,
Henning
--
Henning Rust
Hi,
arima expects an order 4 model by specifying order=c(4,0,0). It looks
like you want to fit an order 6 model with parameters 2 and 3 fixed to
0. Try order=c(6,0,0) and fixed=c(NA,0,0,NA,NA,NA,NA), the last NA is
for the intercept.
Henning
Jenný Brynjarsdóttir wrote:
Hello
I want to fit an
Hi Everyone!
I need to average some graphs of the same plot. How do I do that?
It's a plot of different Kfn-Graphs, but Kaver() only works for simulated
data.
Who can help?
Thx
Deborah
__
[EMAIL PROTECTED] mailing list
Rodrigo Abt a écrit :
Hi everyone,
I'm posting again, since I haven't got an answer (yet :( ).
According to R help, manova does not support the inclusion of the Error()
term in the formula call. I have repeated measures data for two dependent
variables,
so this means I can't account for subject
Ulisses, could you be a little more specific ?. What OS, R version and data
you are using ?
I've tested this as an example and works fine (at least for me):
f-function(){
x-1:10
y-rnorm(10)
s-lm(y~x+0)
summary(s)
}
f()
Call:
lm(formula = y ~ x + 0)
Residuals:
On Wed, 14 Jan 2004, Henning Rust wrote:
Hello,
does anyone know about:
a) simulating seasonal ARIMA models? arima out of package ts can fit it,
but it does not look like it can simulates data from seasonal models
Well, it doesn't simulate at all. arima.sim simulates non-seasonal models
Ok I made Jarque-Bera test to the residuals (merv.reg$residual)
library(tseries)
jarque.bera.test(merv.reg$residual)
X-squared = 1772.369, df = 2, p-value = 2.2e-16
And I reject the null hypotesis (H0: merv.reg$residual are normally
distributed)
So I know that:
1 - merv.reg$residual aren't
Unless 'summary' is the last evaluated object within your function (and
then it is the one implicitely returned by the function), you have to
explicitely ask for printing it:
f - function {
...
model - lm(rttx[,1] ~ rttx[,2] + 0);
# Print summary for the model
I confirmed this -- array(list(), c(2,2)) works in R 1.6.2 and R 1.7.1, but
not in R 1.8.0. This appears to be due to a change in array(): rep(data,
t1) was changed to rep.int(data, t1). When data=list(), t1==Inf, and
rep(data, t1) returns list(), while rep.int(data, t1) gives an
error.
Admittedly this is a rather crytic message but it means that the
algorithm in dgesdd for determining the singular values did not
converge. From the Lapack documentation for dgesdd
INFO(output) INTEGER
= 0: successful exit.
0: if INFO = -i, the i-th
On Wed, Jan 14, 2004 at 04:53:45PM +0100, Eric Lecoutre wrote:
Unless 'summary' is the last evaluated object within your function (and
then it is the one implicitely returned by the function), you have to
explicitely ask for printing it:
Thanks for the explanation
f - function {
Curious.
I get the following error message:
Error in cca.default(cnts94, env94): All row and column sums
must be 0 in the community matrix
Check the row and column sums if you haven't:
colSums(cnts94)
rowSums(cnts94)
There is probably a veg plot (row) that has all zeros in it.
Just a
If there something available in R that has the
functionality of the S-PLUS peaks() function?
Thanks,
Mirka
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
Ok I made Jarque-Bera test to the residuals (merv.reg$residual)
library(tseries)
jarque.bera.test(merv.reg$residual)
X-squared = 1772.369, df = 2, p-value = 2.2e-16
And I reject the null hypotesis (H0: merv.reg$residual are normally
distributed)
So I know that:
1 - merv.reg$residual aren't
Hi all,
A student at our institute asked me for help with the following problem:
After fitting an aov model, she wanted diagnostic plots, and got the
following error message:
plot(p.aov)
Hit Return to see next plot:
Hit Return to see next plot:
Error in plot.window(xlim, ylim, log, asp, ...)
Hello,
I was wondering whether a Poisson mixture modeler/cluster analysis
package is available for R. I scanned CRAN packages and couldn't find
anything but I thought I'd ask. If not could anyone recommend a non-R
open source package. I have found 'snob' but this program seems a bit
hard to use
Hi,
I tried to unsubscribe because this emailadress won't be valid anymore from
next week on. I send a mail to [EMAIL PROTECTED]
with 'unsubscribe'in the body, and got the following reply:
-
Date: Tue, 13 Jan 2004 11:04:11 +0100
From: [EMAIL PROTECTED]
To: [EMAIL PROTECTED]
Subject:
Hi,
thanks for you reply. Actually I think it has more to do with solaris
than with R. The simple workaround is to run the program
interactively.
| Date: Wed, 14 Jan 2004 13:24:02 +0100
| From: Uwe Ligges [EMAIL PROTECTED]
|
| 200M of the data size processed or 200M of RAM consumption by
Dear all,
I want the title of the plot to print some parameters that change. Also, I want some
spots on the plot to be labeled. Is that possible?
Thanks in advance for your help.
Minghua
__
[EMAIL PROTECTED] mailing list
I'm trying to collapse the following table along the sub-group factor. In
this case, collapsing means taking the average ages within a subgroup and
creating a new table. I seem to be running into trouble trying to create
this new data frame. I can use the ave() function to find averages within a
Kurt Sys [EMAIL PROTECTED] writes:
If I'm not a member of the list, why do I recieve the messages?
There was a messup in Zurich causing the outgoing queue to be stalled.
My guess is that you're receiving mails that were sent to you before
your subscription.
--
O__ Peter Dalgaard
Look at ?substitute, ?expression, and ?paste. The archives are dense
with worked examples. Here's one example of a parameter in the title:
param - pi
plot(1:100, log(1:100))
title(substitute(hat(theta) == param, list(param=param)))
A search of the archives for label points plot turns up 100s of
Will aggregate() do what you want?
-roger
Scott Norton wrote:
I'm trying to collapse the following table along the sub-group factor. In
this case, collapsing means taking the average ages within a subgroup and
creating a new table. I seem to be running into trouble trying to create
this new
Hi all,
Earlier today I posted this question on s-news, so apologies to some for
the duplication.
Please put aside your snobbery about Microsoft products for a moment.
I am fitting population models to annual survey data for trout. For those of you familiar with ecological models, I am working
Hello,
I have run a discriminant analysis (with lda() from the MASS package)
but I can't find a way to examine the p-values for the discriminant
functions. I would like to calculate a Wilk's lambda and then the
Bartlett's V statistic which is distributed as a chi squared and test
its
Geoff,
I can offer a work-around.
I have been encountering this same problem on one of two OS X
systems, and one Solaris system. I've been corresponding with the
RMySQL maintainer, David James (who I CC'd), and he knows everything
that I do (and more, of course!). We don't have a proper
Hi there
does anyone know about a downloadable CRAN for copula functions for R?
Not on CRAN, but on my homepage (www.luc.ac.be/~jlindsey/rcode.html).
gausscop in my repeated library handles gaussian copulas.
Jim
Thank you so much for your answers.
Hanspeter
The list could probably be more useful if you gave more details about your
data and the problem. I have written a bit of R code myself for fitting a
finite mixture of univariate Poissons by EM and found it very simple to
program in R. I suspect that your problem is multivariate, but that should
Hello,
my intention is to test a given timeseries (vector) for heteroscedastic.
Now I found the gqtest/bptest/hmctest in the lmtest package but a
formula as argument is needed.
What is meant by formula and how du I interpret the timeseries as
formula.
Thanks in advance
Simon
Ulisses, by the way I forgot something, If your function doesn´t end with
summary you'll have to print it explicitly
f-function(){
x-1:10
y-rnorm(10)
s-lm(y~x+0)
...
print(summary(s))
...
}
---
Date: Wed, 14 Jan 2004 09:24:22 +0100
From: [EMAIL PROTECTED]
Subject: [R] summary() within a
Hello list,
I am new to R, so if the question is rather silly, please ignore it.
I was wondering wether it would be possible to use the models generated
by pam, clara and the like as predictors? Scanning through the available
documentation shed no light (for me) upon the subject.
Regards,
Dear R experts,
How should lambda and gamma (with std.errors) be calculated for a weibull model with
age as an independent predictor? I have assumed that this can be done with survreg
with e. g. (summary(survreg(Surv(time, status) ~ age, dist = 'weibull')) ) and
predict.survreg with e.g.
If pam produces the cluster medoids, you should be able to use the
1-nearest-neighbor classifier for prediction of future data, using the
medoids as the `training' data. 1-NN is available in the `class' package,
part of the `VR' bundle.
HTH,
Andy
From: Renald Buter
Hello list,
I am new
Hello R-users,
first thanks to all who responded my questions regarding the installation
of the Rcmdr and tcltk packages. The problem is with the tclk package on
which Rcmdr depends.
Following Prof Ripley's advice I re-installed Tcl and Tk, compiling from
sources and making sure the
Hello Murray,
thanks for the response. I would actually love to hear alternative
suggestions about the problem I am trying to solve. I just thought a
short question will be less of a burden on people's time and have a
higher chance of being answered.
basically the data sets I need to analyze
Hi:
I have data from an assay in the form of two vectors, one is response
and the other is a predictor. When I attempt to fit a 5 parameter
logistic model with nls, I get converged parameter estimates. I also
get the same answers with gnls without specifying the weights
argument.
However,
I was getting similar errors, which I finally tracked down to the
following:
I had accidentally left an extraneous test.R in my pkg/R directory;
that file contained a system call to an external program that created a
particular file, which I then tried to read into R. The R code that
On Wed, Jan 14, 2004 at 09:10:51PM +0100, Fredrik Lundgren wrote:
Dear R experts,
How should lambda and gamma (with std.errors) be calculated for a weibull model with
age as an independent predictor? I have assumed that this can be done with survreg
with e. g. (summary(survreg(Surv(time,
Hi R-masters,
I have a problem with nls() and my research data. Look this example:
X2000-c(1.205268,2.850695,5.100860,8.571610,15.324513,25.468599,39.623418,61.798856,91.470006,175.152509)
age-c(37,42,47,52,57,62,67,72,77,82)
fit - nls(X2000~R*exp(A*age),start=list(R=.1,A=.1))
Error mensage:
Hi,
I don't know S-Plus and its functions nlminb() and ms(). However, in R I would
use optim(), optimize or nlm(). I used these functions quiet often and had
only very few problems. I think that R is better, easier and more flexible
than Excel (at least in the long run), but since I don't
On Wed, Jan 14, 2004 at 10:45:56PM +0100, Göran Broström wrote:
On Wed, Jan 14, 2004 at 09:10:51PM +0100, Fredrik Lundgren wrote:
Dear R experts,
How should lambda and gamma (with std.errors) be calculated for a weibull model
with age as an independent predictor? I have assumed that
On Wed, 14 Jan 2004, Simon Ohrem wrote:
Hello,
my intention is to test a given timeseries (vector) for heteroscedastic.
Now I found the gqtest/bptest/hmctest in the lmtest package but a
formula as argument is needed.
What is meant by formula and how du I interpret the timeseries as
VR describes binomial GLMs with mortality out of 20 budworms.
Is it appropriate to use the same approach with mortality out of
numbers as low as 3? I feel reticent to do so with data that is not
very continuous. There are one continuous and one categorical
independent variables.
Would it be
I am trying to figure out R data types and/or storage mode. For example:
#From a clean workspace
gc()
used (Mb) gc trigger (Mb)
Ncells 415227 11.1 597831 16
Vcells 103533 0.8 7864326
x - seq(0,10,1)
is.integer(x)
[1] FALSE
is.double(x)
[1] TRUE
object.size(x)
I think that for heatmap, one needs to preprocess the data before passing
it to heatmap. In particular, if you know the row indices of the genes of
interest, you may pass just those rows with or without the row dendrogram.
If one has a dendrogram object, using cutree (see ?cutree) will give
The advisability of using glm with mortality depends not on the
size of sample groups but on the assumption of independence: Whether
you have 3 individuals per group or 30 or 1, is it plausible to assume
that all individuals represented in your data.frame have independent
chances of
Rodrigo Abt [EMAIL PROTECTED] wrote:
According to R help, manova does not support the inclusion of the Error()
term in the formula call. I have repeated measures data for two dependent
variables,
so this means I can't account for subject variance in time?. Any lights?
John Fox's sem
On Wed, 14-Jan-2004 at 05:15PM -0800, Spencer Graves wrote:
| The advisability of using glm with mortality depends not on
| the size of sample groups but on the assumption of independence:
| Whether you have 3 individuals per group or 30 or 1, is it
I think we can assume independence.
Yes, but glm maximizes the binomial likelihood assuming
log(p/(1-p)) is a linear model. Therefore, you don't have to transform
the 0's and 1's. There are cases where a particular combination of
potential explanatory variables will clearly separate mortalities from
survivors. I don't
Bernardo Rangel Tura [EMAIL PROTECTED] writes:
I have a problem with nls() and my research data. Look this example:
X2000-c(1.205268,2.850695,5.100860,8.571610,15.324513,25.468599,39.623418,61.798856,91.470006,175.152509)
age-c(37,42,47,52,57,62,67,72,77,82)
fit -
VR has a binomial glm with binary data, in fact, (e.g. the birth weight
data) and this is quite usual.
Going to large numbers of trials for each probability is really only
important if you plan to use the absolute residual deviance as a test of
fit. With binary data the distribution of the
78 matches
Mail list logo