Dear all,
S+Finmetrics has a number of very specilised functions. I am
particularly interested in the estimation of cointegrated
VARs (chapter
12 of Zivot and Wang). In this context the functions coint() and
VECM() stand out. I looked at package dse1, but found no
comparable
Dear R users,
I would like to know if R has any tools to estimate a finite mixture model.
Many thanks,
Joao Pedro
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
ZABALZA-MEZGHANI Isabelle wrote:
Hello,
I have implemented a method which uses sink to follow the progression status
of an iterative process (Below is part of the code)
I have already used such kind of code with no problem. Today, I get a sink
stack is full error.
I wonder if it could be linked
On Fri, 26 Mar 2004, Joao Pedro W. de Azevedo wrote:
I would like to know if R has any tools to estimate a finite mixture model.
It has several. It is strange you did not want to know what they are, but
for the sake of others who may be intrigued:
See script ch16 in MASS for bivariate
BaRow == Barry Rowlingson [EMAIL PROTECTED]
on Fri, 26 Mar 2004 10:11:04 + writes:
((nicely explaining everything))
...
BaRow . your code (which wasn't attached
BaRow because I think R-news strips out attachments).
R-help (sic) does strip (most)
Hi all,
I am working on Macos x 10.3 (Panther) to build a package consisting of
C/C++ code that is called from R. In the C-sources I use several commands
to print info to the console:
I used two different ways:
std::cout info\n;
And Rprintf(info\n);
Both work fine when R is run from the
I've noticed that the update() function does not seem to work correctly
when offset(..) terms are there:
update(modelwithoffset, .~.-afixedeffect)
drops the offset term.
I'm using this with a negbin model, but I think it goes wrong with the
update.formula() function.
update.formula
function
Hi all,
I'm trying to perform an MDS of some data that I have. When I use
cmdscale everything is fine and I get some interesting results however,
the tends to be low.
What I wnat to do is compare this with the Non-Metric MDS using isoMDS
or sammon. However, when I try using these I get the
Dear R-list member,
an update of package 'urca' has been uploaded to CRAN (Mirror: Austria).
In the updated release unit root and cointegration tests encountered in
applied econometric analysis are implemented. The package is written in
'pure' R and utilises S4 classes.
In particular, the
Hello!
For 2 days can not connect to www.omegahat.org :(
Something happens?
traceroute to www.omegahat.org (128.105.174.32), 30 hops max, 38 byte
packets
..
13 144.92.128.196 (144.92.128.196) 161.792 ms 162.260 ms 160.893 ms
14 g1-2.cisco1.cs.wisc.edu (128.105.1.14) 160.996 ms
I was wondering the same thing.
The traceroute seems to end at their border router, which leads me to
believe that they has a hardware failure.
Hoping that they get it up in a few days.
I've checked around and there are a few mirrors but they all just hang, so I
guess we have to wait...
Mark
On Fri, 2004-03-26 at 15:02, Adam Tee wrote:
Hi all,
I'm trying to perform an MDS of some data that I have. When I use
cmdscale everything is fine and I get some interesting results however,
the tends to be low.
What I wnat to do is compare this with the Non-Metric MDS using isoMDS
Mark Fowle wrote:
I was wondering the same thing.
The traceroute seems to end at their border router, which leads me to
believe that they has a hardware failure.
Hoping that they get it up in a few days.
I've checked around and there are a few mirrors but they all just hang, so I
guess we have to
On Thu, 2004-03-25 at 17:42, Itay Furman wrote:
Thanks, Marc, for your reply.
Happy to help.
I didn't explain myself well, but thanks to you I think I could
phrase my question better.
I want to be able to compute new tick-positions for the top
X-axis.
Why new ticks positions?
See in
Just a quick and probably simple question:
dat - rnorm(500,sd=1+(1:500)/500)
fun - function(x) t.test(x)$p.value
running(dat,width=50,fun=fun,allow=T)
Error in t.test.default(x) : not enough x observations
running(dat,width=50,fun=fun,allow=F)
Error in t.test.default(x) : not enough x
i need to know how to estimate a linear regression whose coefficients sum
to zero
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Good morning.
I'm a complete tyro at using R, having downloaded it yesterday for the
sole purpose of running a problem in PAN, Joe Schafer's program for
multiple imputation of multilevel data.
I'm starting to get the hang of the command interface, and *think* I have
all the input matrices
Why does stop(we are done) print
Error in eval.with.vis(expr, envir, enclos) : ?
It would seem to me that a plain stop() is not an error, and that it
would make more sense to have an error() function that is different from
a stop(). Is there a rationale here that I am missing?
sincerely,
I got a suggestion offlist that I go ahead and post my R commands:
lib(pan)
y - read.table(c:/temp/y.dat, header=TRUE, na.string='.')
subj - read.table(c:/temp/subj.dat, header=TRUE)
pred - read.table(c:/temp/pred.dat, header=TRUE, na.strings='.')
xcol - c(1, 2, 3, 4, 5, 6, 7, 8)
zcol - c(1, 6,
i need to know how to estimate a linear regression whose coefficients sum
to zero
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Please do read the documentation of the functions you are trying to use.
The description in ?stop says:
'stop' stops execution of the current expression and executes an
error action.
stop() is how error is flagged in R (and S in general). If that's not what
you want, try something
i need to know how to estimate a linear regression whose coefficients sum
to zero
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Hi there,
No information was found which version of XFree86 get along with R. I
could not compile R version 1.8.1 with XFree86 4.3.99.902.
Here is error message.
gcc -I. -I../../../src/include -I../../../src/include -DI18N_MB -I/usr/X11R6/include
-I/usr/local/include -DHAVE_CONFIG_H
It says not enough x observations. That's pretty clear.
So ask yourself, what is the minimum number of observations one needs
to do a t test?
Try this to see how many observations t.test was given each time.
running(dat,width=50,fun=function(x) length(x),allow=T)
or this
Dear Danlin Yu:
I read your message at https://stat.ethz.ch/pipermail/r-help/2003-April/030754.html.
Actually, I have a question about significant of Local Moran I too. based on it's
function:
Ii = zi [¦²j wijzj],
I wonder how can I calculate it's z-value.
Any
Assuming that you want to estimate via least squares, you can
do something like this:
reg.coefsum - function(x, y, start=coef(lm.fit(x, y)), coefsum=0,
penalty=1000) {
subfun.objective - function(coef){
sum((y - x %*% coef)^2) + abs(sum(coef)) * penalty
}
opt -
It isn't clear that R is currently friendly to the new XFree 4.4
license. I believe that there is an advertising clause for linking --
does anyone know if this has been addressed or clarified? I've not
been following those issues for a few months.
best,
-tony
Susumu
I couldn't find any reference to this in the FAQ, but is it possible to sort
a dataframe by multiple columns?
I've created some code, similar to the following:
nspr.code - sp.results$sp.code[order( sp.results$sp.code )]
nspr.tpa - sp.results$tpa[order( sp.results$sp.code )]
nspr.code -
The function has a coefsum argument but never uses it.
The objective is supposed to be:
sum((y - x %*% coef)^2) + abs(sum(coef) - coefsum) * penalty
Patrick Burns wrote:
Assuming that you want to estimate via least squares, you can
do something like this:
reg.coefsum - function(x,
Consider a regression equation say:-
Y=a+b1*X1+b2*X2+b3*X3
if all the regression coefficients have to sum to 0
then
a+b1+b2+b3=0
i.e.
b3=-a-b1-b2
Substituting this back into the regression equation we get
Y=a(1-X3)+b1(X1-X3)+b2(X2-X3)
All you need to do then is to create the new
I am attempting to plot something called a (marginal) dot diagram which is a regular
scatterplot with an extra set of plots in the margins along both the X and Y axes. I
have looked everywhere I can think for information. Can anyone give me any
suggestions? Is there a single command that
?order
Jeff D. Hamann wrote:
I couldn't find any reference to this in the FAQ, but is it possible to sort
a dataframe by multiple columns?
I've created some code, similar to the following:
nspr.code - sp.results$sp.code[order( sp.results$sp.code )]
nspr.tpa - sp.results$tpa[order(
On Fri, 2004-03-26 at 10:41, [EMAIL PROTECTED] wrote:
I am attempting to plot something called a (marginal) dot diagram
which is a regular scatterplot with an extra set of plots in the
margins along both the X and Y axes. I have looked everywhere I can
think for information. Can anyone give me
Also try ?rug
On Fri, 2004-03-26 at 10:41, [EMAIL PROTECTED] wrote:
I am attempting to plot something called a (marginal) dot diagram
which is a regular scatterplot with an extra set of plots in the
margins along both the X and Y axes. I have looked everywhere I can
think for
pnick at virgilio.it writes:
i need to know how to estimate a linear regression whose coefficients sum
to zero
Transform the model:
y = Xb + error
to
y = XPb + error
where P is the projection onto the orthogonal complement of the vector 1.
Solve this regression for b and then Pb
Dear list members,
I am trying to use the maptools library to display geographical data. At
the moment I have some trouble understanding how the auxvar variable
is supposed to be used in the plot.Map function.
I am using R Version 1.8.1 (2003-11-21) on Linux
Looking at the plot.Map
A student (at another university) has contacted me for advice about a
good text dealing with the general linear model (which she needs to
know about for her thesis defense).
[One might say that if she used the GLM in her thesis she ***ought***
to know about the concept already, but ought to and
Dear All,
I need help both with analytical and computational aspects.
My problem: I have counted and measured increments on otoliths (inner-ear bony
structures) of fish larvae collected at different times of day. This was
repeated three times for each fish larvae (in random order and no
On Fri, 2004-03-26 at 10:30, A.J. Rossini wrote:
It isn't clear that R is currently friendly to the new XFree 4.4
license. I believe that there is an advertising clause for linking --
does anyone know if this has been addressed or clarified? I've not
been following those issues for a few
Uwe Ligges [EMAIL PROTECTED] writes:
Mark Fowle wrote:
I was wondering the same thing.
The traceroute seems to end at their border router, which leads me to
believe that they has a hardware failure.
Hoping that they get it up in a few days.
I've checked around and there are a few
Friends:
1. Is it possible to import data from excel and/or access to R? How?
2. Is it possible to import data from a txt file? How?
Thanks in advance,
Ricardo.
[[alternative HTML version deleted]]
__
[EMAIL PROTECTED] mailing list
Sorry to take up bandwidth, but
Several people have already sent my suggestions
for books about ***generalized*** linear models.
My request was for suggestions as to books on
***GENERAL*** linear models, which is an (entirely?)
different topic.
There is a Data Import/Export manual.
Check it!
For 2. see ?read.table
On Fri, 26 Mar 2004, Ricardo Huaman wrote:
Friends:
1. Is it possible to import data from excel and/or access to R? How?
2. Is it possible to import data from a txt file? How?
Thanks in advance,
Ricardo.
On Fri, 26 Mar 2004, Marco Albani wrote:
Dear list members,
I am trying to use the maptools library to display geographical data. At
the moment I have some trouble understanding how the auxvar variable
is supposed to be used in the plot.Map function.
I am using R Version 1.8.1
On Sat, 27 Mar 2004, [gb2312] Louis wrote:
Dear Danlin Yu:
I read your message at
https://stat.ethz.ch/pipermail/r-help/2003-April/030754.html. Actually,
I have a question about significant of Local Moran I too. based on it's
function:
Ii = zi [¦²j wijzj],
Dear all
Why isn'it possible to calculate Mahalanobis distances with R for a matrix
with 1 row (observations) more than the number of columns (variables)?
mydata - matrix(runif(12,-5,5), 4, 3)
mahalanobis(x=mydata, center=apply(mydata,2,mean), cov=var(mydata))
[1] 2.25 2.25 2.25 2.25
mydata
On Fri, 26 Mar 2004, Marco Albani wrote:
Roger Bivand wrote:
On Fri, 26 Mar 2004, Marco Albani wrote:
At
the moment I have some trouble understanding how the auxvar variable
is supposed to be used in the plot.Map function.
[...]
I don't seem to be able to get any information on
hi andy: yes, I know what it does. My suggestion would be to have a
different command, that is a pure stop without error condition (with
its message). A stop and an error are really two different things.
regards, /ivo
Liaw, Andy wrote:
Please do read the documentation of the functions you
Douglas Bates [EMAIL PROTECTED] writes:
The machine that was serving as Omegahat.org was compromised. We were
going to move that site to another machine anyway so this attack has
resulted in a somewhat accelerated schedule for the move.
Before any one get's unduly paranoid: There's nothing
The thing is that functions don't really stop... they return. So what you
want is return()
Cheers, Pierre
ivo welch wrote:
hi andy: yes, I know what it does. My suggestion would be to have a
different command, that is a pure stop without error condition (with
its message). A stop and an
Which version of R? This is supposedly fixed in 1.9.0 beta, so please try
that.
On Fri, 26 Mar 2004, Simon.Bond wrote:
I've noticed that the update() function does not seem to work correctly
when offset(..) terms are there:
update(modelwithoffset, .~.-afixedeffect)
drops the offset
If you `lie', you may find that the routines fail to converge, especially
sammon -- it is not a good idea.
On 26 Mar 2004, Jari Oksanen wrote:
On Fri, 2004-03-26 at 15:02, Adam Tee wrote:
Hi all,
I'm trying to perform an MDS of some data that I have. When I use
cmdscale everything
And a closer examination of the help page would lead you to this:
options(show.error.messages=FALSE)
stop()
which is what I believe you want
Jim
James W. MacDonald
Affymetrix and cDNA Microarray Core
University of Michigan Cancer Center
1500 E. Medical Center Drive
7410 CCGC
Ann Arbor MI
The following were the replies to my question
about using R's LAPACK and other .h files in
some of my C programs. From what was
said, it appears that buying a ready-made
library (MKL = $200, for example)
or using CLapack according to the Shumway lecture
notes are the best approaches:
If I'm not mistaken, the data you generated form a simplex in the
p-dimensional space. Mahalanobis distance for such data, using sample mean
and covariance, just give the distance to the centroid after normalization.
The normalization step make all the points equidistance from the centroid.
To
Hi,
This is Yan, a graduate student from Temple University. My
current work involves drawing 3D plot in R or S-Plus. I have
a dataset containing distances between 18 cities in 4
continents. Using classical multi-deminsional scaling in 2
dimensions, I could seperate them successfully and plot
Note this is not R as distributed by R-core (which does not have
dataentry_mb.c) but I believe some `Japanized' distribution. People might
want to check if the problem is in the changes (which I suspect) or R
itself.
On Fri, 26 Mar 2004, A.J. Rossini wrote:
It isn't clear that R is currently
Nick Efthymiou has created two R packages out of some
of the functions from S Poetry. He obviously realized that
I'm too much of a slouch to do it myself.
They are Nick's packages, but they are available through
the S Poetry page on http://www.burns-stat.com
The packages are:
To the extent that my daughter, work and sports activities leave me
some time, for sure I will put together a function like AggregateSeries
(maybe within the its package)! As for cointegration, much less likely
to happen, especially in light of the development of the urca package.
The
Greetings:
I'm trying to annotate a plot and find that I cannot correctly paste
elements. When I do this:
text(1.4, 1., paste(conditional density, \n, of y, given ,
expression(x == x[0])), adj=c(0.,0.))
The expression is not properly displayed.
Resolving this is not urgent because the
Thanks to all once again for the very useful suggestions. I will have
to teach myself some real S before tackling the writting of the
AggregateSeries-like function! I brace myself.
Kind regards,
Ivan
___
Ivan Alves
mailto://[EMAIL PROTECTED]
Prof Brian Ripley [EMAIL PROTECTED] writes:
Note this is not R as distributed by R-core (which does not have
dataentry_mb.c) but I believe some `Japanized' distribution. People might
want to check if the problem is in the changes (which I suspect) or R
itself.
Yes. On the other hand, the
Charles Annis, P.E. [EMAIL PROTECTED] writes:
Greetings:
I'm trying to annotate a plot and find that I cannot correctly paste
elements. When I do this:
text(1.4, 1., paste(conditional density, \n, of y, given ,
expression(x == x[0])), adj=c(0.,0.))
The expression is not properly
[The new version of gregmisc will be showing up on CRAN shortly.]
-Original Message-
From: Warnes, Gregory R
Sent: Friday, March 26, 2004 6:07 PM
To: 'Sean Davis'
Subject: RE: Quick running question
Hi Sean,
Congratulations, you found a bug!
My running function took an improper
Warnes, Gregory R would like to recall the message, Quick running
question.
LEGAL NOTICE\ Unless expressly stated otherwise, this messag...{{dropped}}
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
PLEASE do
[The new version of gregmisc will be showing up on CRAN shortly.]
-Original Message-
From: Warnes, Gregory R
Sent: Friday, March 26, 2004 6:07 PM
To: 'Sean Davis'
Subject: RE: Quick running question
Hi Sean,
Congratulations, you found a bug!
My running function took an
Hello all,
I'm having trouble installing the package 'gregmisc'. I've run the
command:
R CMD INSTALL -l /usr/lib/R/library /tmp/gregmisc_0.9.0.tar.gz
And I can see it shows up on the list of available packeage when I issue
library()
But when I do
library(gregmisc)
I get:
Error in
So you still have not told us what exactly what you are looking for. What
do you want some sort of stop() to do inside a function, that is neither an
error nor returning? Can you show an example in some other language that
has such a feature?
Andy
From: ivo welch [mailto:[EMAIL PROTECTED]
Hi all,
Is it possible to run kmeans, pam or clara with a constraint such that
no resulting cluster has fewer than X cases?
These kmeans algorithms often find clusters that are too small for my
use. There are usually a few clusters with 1-10 cases (generally
substantial outliers). I then have
Andy,
I'm really not sure that he hasn't told us. All he wants to do is stop the
process, without throwing an error. return() won't work if he's in a nested
function, it will just send him up to the next level. For example, let's say
he's in a loop and calling his function in the loop. If
OK... how about defining a function exit() as follows
exit - function() {
+ opt - options(show.error.messages=FALSE)
+ on.exit(options(opt))
+ stop()
+}
then
spend.time - function(i) {
+ print(i)
+ if (i == 5) {
+ exit()
+ }
+ if (i == 75) {
+ stop(Is this an error?)
+
Hi,
Shouldn't the following commands produce a nice jpeg file, or am I
missing something?
hist(rnorm(1000))
dev.print(file=test.jpg,device=jpeg)
I get a very tiny (6x6 pixel) jpeg every time. Using
dev.copy(file=test.jpg,device=jpeg) ; dev.off()
instead of dev.print produces a perfectly
Hi,
I've written some helper functions which are used by another function
(called func()). When func() is sourced I dont want the helper function
to be seen in the global namespace (as shown by ls()).
Currently what I have done is:
func - function() {
helper1 - function() {
...
}
On Fri, Mar 26, 2004 at 09:25:02PM -0500, Scott Bartell wrote:
Shouldn't the following commands produce a nice jpeg file, or am I
missing something?
hist(rnorm(1000))
dev.print(file=test.jpg,device=jpeg)
[...]
R bug or my misunderstanding?
The latter. The idiom is
Here's one possible alternative:
- Write the helper functions outside of func().
- source() the file containing all the functions.
- save(helper1, helper2, file=helperfuns.rda)
- rm(helper1, helper2)
- attach(helperfuns.rda)
Eventually you may want to put things into a package...
HTH,
Andy
OK, I guess I'm dense (again?)...
Stop where, and do what? I don't know many languages, but I haven't seen
(or heard) any that allows stopping in the middle of a function and do
nothing. What's the poor user to do at that point?
The only thing I could think of is when the programmer is
Hello
getdata - function(p){
fname - NULL; dl - list(NULL)#build the sturcture
dt - read.csv(file.path(d,i),header=F) #data frame
ret - builddl(dt,s) #where s is a string
}
how can I get this following function to use fname and
dl from the above function without passing them down
the
77 matches
Mail list logo
