Hi
On 12 Mar 2003 at 15:45, Shutnik wrote:
> Dear friends,
> I work with Matlab and now a bit in trouble with getting used to R.
> Could you give me some help with the following questions:
>
> 1. how to generate the random matrix mxn with constant mean and
> variance, say N(0,1)?
>
> 2. h
On Wed, 12 Mar 2003, Spencer Graves wrote:
> If you want to use nlme, am I correct is asserting that the best
> reference is
>
> Pinhiero and Bates (2000) Mixed Effects Models in S and S-Plus (NY:
> Springer) ?
Yes.
There are several other ways to do this though, and I don't think I would
st
If you want to use nlme, am I correct is asserting that the best
reference is
Pinhiero and Bates (2000) Mixed Effects Models in S and S-Plus (NY:
Springer) ?
Spencer Graves
kjetil brinchmann halvorsen wrote:
On 12 Mar 2003 at 2:37, Blaise TRAMIER wrote:
You should have a look at the package n
On Wed, 12 Mar 2003, kjetil brinchmann halvorsen wrote:
> On 12 Mar 2003 at 19:50, Uwe Ligges wrote:
> > I would vote against comparing different model classes using AIC.
>
> Why? I thought one of the advantages with AIC is that it can be used
> to compare different model classes, although in p
On Wed, 12 Mar 2003 13:01:12 +0100
vito muggeo <[EMAIL PROTECTED]> wrote:
> Dear all,
> I'm looking for someone that help me to write an R function to simulate
> survival data under complex situations, namely time-varying hazard ratio,
> marginal distribution of survival times and covariates. The
On Thu, 13 Mar 2003, Robin Hankin wrote:
> Hi everyone.
>
> What's going on here?
>
>
> > a <- matrix(1:4,2,2)
> > a
> [,1] [,2]
> [1,]13
> [2,]24
> > apply(a,2,sum)
> [1] 3 7
> > apply(a,2,"+")
> [,1] [,2]
> [1,]13
> [2,]24
> > apply(a,1,"+")
> [,1]
Hi everyone.
What's going on here?
> a <- matrix(1:4,2,2)
> a
[,1] [,2]
[1,]13
[2,]24
> apply(a,2,sum)
[1] 3 7
> apply(a,2,"+")
[,1] [,2]
[1,]13
[2,]24
> apply(a,1,"+")
[,1] [,2]
[1,]12
[2,]34
>
help(apply) says that "+" should be
Hola!
I am about to do this years buying for our library, and could need
help with some references.
Some people here will start to work with IRT and Rasch models.
>From the book descriptions on Amazon it is difficult to decide
what books to buy.
I want one introductory book on IRT/Rasch, and
On 12 Mar 2003 at 2:37, Blaise TRAMIER wrote:
You should have a look at the package nlme, installed with your
distribution of R. Look at the help for the function
lme (linear mixed models). You have not described your data
sufficiently to say much more, but you have biological measurements
chan
On 12 Mar 2003 at 19:50, Uwe Ligges wrote:
.
.
.
.
> I would vote against comparing different model classes using AIC.
Why? I thought one of the advantages with AIC is that it can be used
to compare different model classes, although in practice it might be
difficult because programs delete con
On Wed, 12 Mar 2003, Jim McLoughlin wrote:
> /*
> * Wrapper for use in R - requires that return value by passed via
> argument
> */
> void blackScholesR( double *S, double *K, double *r, double *T, double
> *volatility, double *price)
> {
> *price = blackScholes(*S, *K, *r, *T, *volatilit
Hi folks
I'm relatively new to R, and am having some problems using a c function
I'm calling.
The function is loaded, and it works for when given specific (scalar)
arguments, but does not work when passed Vector arguments, and
therefore fails in the outer product I need.
Here are the details:
Dear R-Helpers,
I would like to read an Excel .xls file via RODBC. I have successfully run
the example in p. 18 of "R Data Import/Export". The problem I am facing is
that Excel's ODBC driver seems to have a limit on the number of
fields/columns (output below). I haven't found any documentation on
Allin Cottrell wrote:
Sorry, here's one:
library(tseries)
data(EuStockMarkets)
dax <- diff(log(EuStockMarkets))[,"DAX"]
dax.garch <- garch(dax)
png()
plot(dax.garch)
dev.off()
I can confirm that the problem exists in the latest development sources
under RedHat 7.3. I'm teaching in bit, but I'll
Hi,
I have a function which does a certain task with two vectors,
f1 <- function(a,b){body}
I also have a list of matrixes (all with the same dim's), and for each
column of each matrix in the list I want to use "f1", in such way that
it gives the vector "a" in the first argument of "f1". The se
<> <> <> <>
Indeed, the problem persists. My code was using a for() loop:
##
png()
for (i in seq(1, 16, 4)) {
par(mfrow=c(2, 2))
for (gt in i:(i+3)) {
mysep <- paste(rep(' ', i), collapse='')
plot(density(rnorm(1000)), main=paste(i, gt, sep=mysep))
for (j in 1:5) {
png() and bitmap(), the latter using ghostscript.
On Wed, 12 Mar 2003, Allin Cottrell wrote:
> On Wed, 12 Mar 2003 [EMAIL PROTECTED] wrote:
>
> > And your platform is? There are two different png devices in R.
> >
> > On Wed, 12 Mar 2003, Allin Cottrell wrote:
> >
> > > I saw in the archive a p
On Wed, 12 Mar 2003, Peter Dalgaard BSA wrote:
> Allin Cottrell <[EMAIL PROTECTED]> writes:
>
> > I am seeing the same thing (with R 1.6.2 on Linux i686). My input
> > file generated 4 plot files. The first two were fine, but the last 2
> > featured a weird overlay of the remaining graphs. The
On Wed, 12 Mar 2003 [EMAIL PROTECTED] wrote:
> And your platform is? There are two different png devices in R.
>
> On Wed, 12 Mar 2003, Allin Cottrell wrote:
>
> > I saw in the archive a post from Mark Wilkinson (Feb 1, 2003), saying
> > that some of his R-generated png plots came out overlapping
Allin Cottrell <[EMAIL PROTECTED]> writes:
> I am seeing the same thing (with R 1.6.2 on Linux i686). My input
> file generated 4 plot files. The first two were fine, but the last 2
> featured a weird overlay of the remaining graphs. The problem is not
> seen with postscript of pdf output.
Ple
And your platform is? There are two different png devices in R.
On Wed, 12 Mar 2003, Allin Cottrell wrote:
> I saw in the archive a post from Mark Wilkinson (Feb 1, 2003), saying
> that some of his R-generated png plots came out overlapping.
>
> I am seeing the same thing (with R 1.6.2 on Linux
I saw in the archive a post from Mark Wilkinson (Feb 1, 2003), saying
that some of his R-generated png plots came out overlapping.
I am seeing the same thing (with R 1.6.2 on Linux i686). My input
file generated 4 plot files. The first two were fine, but the last 2
featured a weird overlay of th
On Wed, 12 Mar 2003, Paolo Tenconi wrote:
> Hello,
> I've a question: I invoke R from a text editor in a Win2000 operating system using
>
> Rcmd.exe BATCH inFile outFile
>
> I've two problems:
> a) If I use windows() as graphics device, all windows close immediately after script
> execution,
>
Hello,
I've a question: I invoke R from a text editor in a Win2000 operating system using
Rcmd.exe BATCH inFile outFile
I've two problems:
a) If I use windows() as graphics device, all windows close immediately after script
execution,
how can I let them not to die?
b) Is it possible to redi
1) A quasi- mode does not have a likelihood and so does not have an AIC,
by definition.
2) There is nothing wrong with a negative AIC, but you don't have one.
The value of AIC in your problem is 211.079 + 2*16 + 2. It is summary.glm
that is giving you misleading results. Try the following
log
Vicente Piorno wrote:
>
> Dear R users,
> I am having problems trying to fit quasipoisson and negative binomials glm.
> My data set
> contains abundance (counts) of a species under different management regimens.
> First, I tried to fit a poisson glm:
>
> > summary(model.p<-glm(abund~mgmtcat,po
"Barker, Chris" wrote:
>
> A colleague suggested that some R software was available for estimating
> "Independent Components Analysis" (ICA) (... signal separation).
>
> If so, I'd appreciate any pointers .
>
> Chris Barker
>Director of Statistical Research
> MEDTAP Interna
On CRAN there is package fastICA and an ica function in package e1071
On Wed, 12 Mar 2003, Barker, Chris wrote:
> A colleague suggested that some R software was available for estimating
> "Independent Components Analysis" (ICA) (... signal separation).
>
> If so, I'd appreciate any pointers .
Dear R users,
I am having problems trying to fit quasipoisson and negative binomials glm.
My data set
contains abundance (counts) of a species under different management regimens.
First, I tried to fit a poisson glm:
> summary(model.p<-glm(abund~mgmtcat,poisson))
Call:
glm(formula =
A colleague suggested that some R software was available for estimating
"Independent Components Analysis" (ICA) (... signal separation).
If so, I'd appreciate any pointers .
Chris Barker
Director of Statistical Research
MEDTAP International, Inc.
Redwood City, Ca
Dear friends,
I work with Matlab and now a bit in trouble with getting used to R. Could
you give me some help with the following questions:
1. how to generate the random matrix mxn with constant mean and variance,
say N(0,1)?
2. how to create a code (function), say "myfunction", and make it
juli g. pausas wrote:
Hi,
Given a correlation matrix, how can I know which variables have certain
correlation values?
aa <- matrix( rnorm(25, 1,1), 5,5)
colnames(aa) <- c("v1", "v2", "v3", "v4", "v5")
aacor <- cor(aa)
For instance, which variables are negatively correlated?
aacor[aacor<0]
Spencer Graves wrote:
Regarding 1 and 2:
myfunction <-
function(m=2, n=3)
array(rnorm(m*n), dim=c(m, n))
myfunction()
I'll let someone else answer 3.
Spencer Graves
Shutnik wrote:
Dear friends,
I work with Matlab and now a bit in trouble with getting used to R.
Could you give me some help
On Wed, 12 Mar 2003, juli g. pausas wrote:
> Hi,
> Given a correlation matrix, how can I know which variables have certain
> correlation values?
>
> aa <- matrix( rnorm(25, 1,1), 5,5)
> colnames(aa) <- c("v1", "v2", "v3", "v4", "v5")
> aacor <- cor(aa)
>
> For instance, which variables are nega
Regarding 1 and 2:
myfunction <-
function(m=2, n=3)
array(rnorm(m*n), dim=c(m, n))
myfunction()
I'll let someone else answer 3.
Spencer Graves
Shutnik wrote:
Dear friends,
I work with Matlab and now a bit in trouble with getting used to R. Could you give me
some help with the following q
Hi,
Given a correlation matrix, how can I know which variables have certain
correlation values?
aa <- matrix( rnorm(25, 1,1), 5,5)
colnames(aa) <- c("v1", "v2", "v3", "v4", "v5")
aacor <- cor(aa)
For instance, which variables are negatively correlated?
aacor[aacor<0] # provide the r values,
Dear Michael,
If your dataset is large, you may consider my package savetable at
www.obs.ee/~siim/savetable_0.2.1.tar.gz
This is more memory-efficient than write.table. Unfortunately, I have
not a window binary.
Best wishes,
Ott
| Date: Wed, 12 Mar 2003 05:13:04 -0800 (PST)
| From: Michael
Do you compute the singular value decomponsition of your gradients?
Unless you compute a marginal likelihood using Monte Carlo integration,
I would expect convergence problems to be evident in the range of the
absolute values of the singular values of the gradients: If the
smallest is less tha
Dear friends,
I work with Matlab and now a bit in trouble with getting used to R. Could you give me
some help with the following questions:
1. how to generate the random matrix mxn with constant mean and variance, say N(0,1)?
2. how to create a code (function), say myfunction, and make it
On Wednesday, March 12, 2003, at 12:13 pm, [EMAIL PROTECTED] wrote:
On Wed, 12 Mar 2003, p.b.pynsent wrote:
I have used polygon() to mark the confidence limits of a survival
curve.
In another project, I have used the col parameter to fill my boxplots.
The poly() description refers to filling
Michael Miettinen wrote:
Hi,
Sorry about making this stupid question, but I did not
find the answer from documentation.
I managed to read my spss .sav file into the R, no
problem. Next I would like to write this data to a
file in ascii-format. I tried to use write.table and I
got no error mess
Wow, this is really active list. I got several
friendly answers - many on them asking me to read
documentation better.
I found this software just today, and I may was more
eager to try it out than I should have been. :-)
I promise to use more time with documents before my
next question.
Than
- Original Message -
From: "Michael Miettinen" <[EMAIL PROTECTED]>
To: <[EMAIL PROTECTED]>
Sent: Wednesday, 12 March, 2003 2:13 PM
Subject: [R] Simple question about export
> Hi,
>
> Sorry about making this stupid question, but I did not
> find the answer from documentation.
>
> I managed
The University of Miami's Rosenstiel School of Marine and Atmospheric
Sciences (RSMAS) is seeking a research associate to work with
hydrographic data. The objective of the project is to develop
statistical models for estimating salinity and density from
observations of temperature together with kn
Hi
On 11 Mar 2003 at 16:28, Don Armstrong wrote:
> On Tue, 11 Mar 2003, Marc Schwartz wrote:
> > Finally, you might also consider using the 'cex' argument in both
> > plot() and points(), which can reduce the size of the plotting
> > symbols. The default for par(cex) is 1.0, so you might try smal
If that is what you tried, then you didn't supply the object to the
write.table function.
e.g. if your data.frame is called mydata in R you need
write.table(mydata,"c:/foo/data.dat")
The file is ascii. Note also that you either have to use forward slashes (as
above) or double backslashes
write.t
Well, you did not specify the object to save in write.table(). Suppose
you want to save the following:
x <- matrix( c(1:25), nrow=5)
write.table(x, file="c:/my.output.file.txt")
If all goes well, you should see the prompt without any message.
Also use "/" rather than "\" as it is reserved for e
On Wed, 12 Mar 2003, Michael Miettinen wrote:
> Sorry about making this stupid question, but I did not
> find the answer from documentation.
See the FAQ question 7.10 How do file names work in Windows?
> I managed to read my spss .sav file into the R, no
> problem. Next I would like to write
Dear R users,
I have been doing some eof analysis using princomp function, then the eof
results were rotated with varimax and promax functions. Those functions are
working fine. However, after their uses, I cannot find how to obtain the
temporal evolution and the variance of the obtain component
Hi,
Sorry about making this stupid question, but I did not
find the answer from documentation.
I managed to read my spss .sav file into the R, no
problem. Next I would like to write this data to a
file in ascii-format. I tried to use write.table and I
got no error messages, but no file either.
On Wed, 12 Mar 2003, p.b.pynsent wrote:
> I have used polygon() to mark the confidence limits of a survival curve.
> In another project, I have used the col parameter to fill my boxplots.
>
> The poly() description refers to filling but actually produces
Did you mean polygon()?
> hatching (i.
Dear all,
I'm looking for someone that help me to write an R function to simulate
survival data under complex situations, namely time-varying hazard ratio,
marginal distribution of survival times and covariates. The algorithm is
described in the reference below and it should be not very difficult t
I have used polygon() to mark the confidence limits of a survival curve.
In another project, I have used the col parameter to fill my boxplots.
The poly() description refers to filling but actually produces
hatching (i.e. lines ).
boxplot() does truly fill the boxes with a colour or shades of gre
The majority of the functionality present in the gstat stand-alone
program (http://www.gstat.org/) is now available as a package/library for
the S language (R, S-Plus), again called gstat. The package provides
multivariable geostatistical modelling, prediction and simulation, as
well as several vis
Hi again
With arima0 the problem was solved but what are the diferences
between arima and arima0?
I have another question. I fit the model to the data and I make
some predictions. But I also want to calculate MAPE based in
the last 3 observations available. Is it possible? Can I obtain
the fitted
Thank you!
Adding asp=1 to the plot-command does exactly what I want!
bye,
till
>-- Original Nachricht --
>From: [EMAIL PROTECTED]
>Date: Wed, 12 Mar 2003 07:15:30 + (GMT)
>To: Thomas W Blackwell <[EMAIL PROTECTED]>
>cc: Till Baumgaertel <[EMAIL PROTECTED]>,
>r-help <[EMAIL PROTECTED]
- Original Message -
From: "Eric ESPOSITO" <[EMAIL PROTECTED]>
To: <[EMAIL PROTECTED]>
Sent: Wednesday, March 12, 2003 8:46 PM
Subject: [R] How to collect the Rtools to build packages
> After reading the readme.packages file, I would like to install the R
tools
> in order to build my own
Dear list,
this is not a particular R question but perhaps someone can help.
I am running a maximum likelihood estimation (competing risk duration
model with unobserved heterogeneity) on 30 different datasets. The
problem is that on 2 datasets the model does not converge. I am
interested if the
It _is_ working: I have just checked from outside Oxford. It was
unavailable for a few hours on Saturday (the server was being upgraded)
but has otherwise been up (and that file downloaded successfully several
times a day) for all of the last ten days.
ftp://ftp.stats.ox.ac.uk/pub/Rtools/tools.
After reading the readme.packages file, I would like to install the R tools
in order to build my own packages, but the internet portal
http://www.stats.ox.ac.uk/pub/Rtools/ hasn't been working since a few days.
Where can I get the file tools.zip?
Thank you!
Eric Esposito
__
On Tuesday 11 March 2003 05:00 pm, Till Baumgaertel wrote:
> Hi,
>
> how can I scale the x- and y-axis of a "plot" to the same scale?
>
> My problem: The following command sequence produces the plot in a square.
> What I want is the x-axis to be 5 times as wide (measured e.g. in pixels)
> as the y-
On Wed, 12 Mar 2003, Till Baumgaertel wrote:
> Hi,
>
> how can I scale the x- and y-axis of a "plot" to the same scale?
>
> My problem: The following command sequence produces the plot in a square.
> What I want is the x-axis to be 5 times as wide (measured e.g. in pixels)
> as the y-axis is lon
62 matches
Mail list logo
