Hi,
I'm currently working on porting some SAS scripts to R, and hence need
to do the same calculation (and get the same results) as SAS in order to
make the transition easier for users of the script.
In the script, I'm dealing with a two-factorial repeated-measures anova.
I'll try to give you a
Peter Dalgaard [EMAIL PROTECTED] writes:
Ken Knoblauch [EMAIL PROTECTED] writes:
Here is something quick dirty for Mac that may be serviceable in
some cases, while awaiting someone with greater understanding of
programming connections than I have currently.
With the following copied to
Am Donnerstag, 17. Februar 2005 00:03 schrieb Radha Chebolu:
Hi,
. Also, does R let us import
data from an excel spreadhsheet?
Yes, there are very helpful examples in import/export data in your R
documentation help.start() . AFAIR, there is also an example on how
to import excel sheets to R
Dear Jamie
I already thought that your data structure could be more
complicated than in the example.
I would be careful anywhere. Since there is a difference in the
results of se.contrasts() in R-devel and the results from lme
(and the with lme consistent results of the aggregated data)
in this
Bela Bauer [EMAIL PROTECTED] writes:
Hi,
I'm currently working on porting some SAS scripts to R, and hence need
to do the same calculation (and get the same results) as SAS in order
to make the transition easier for users of the script.
In the script, I'm dealing with a two-factorial
Hi there,
I made a plot with histogram and the curve of kernel density estimation
together. The question is to add a legend to it. What I want is to use a
small box with shade representing the histogram and a line representing
the kernel estimation. Is there any way to implement this?
Thanks a
JTW wrote:
Dear List:
I am trying to understand how to use the
jarque.bera.test() function of the tseries package.
A numeric vector or time series seems to be the only
argument required. What is the default significance
level for rejecting the null of normality?
Is there a way to specify
Jessica Higgs wrote:
Sorry to bother everyone, but I've looked in all of the help files and
manuals I have and I can't find the answer to this question. I'm doing
principle component analysis by calculating the eigen vectors of a
correlation matrix that I have that is composed of 21
Hi
If I understand correctly
barplot(rbind(table(x), table(y)), beside=T)
does what you want.
Cheers
Petr
On 18 Feb 2005 at 7:51, T Petersen wrote:
Almost. Catagories aren't stacked - I would like to see that x has 2
instances of 1 while y has 1 instance of 1. What's more, there are
now
On Fri, 2005-02-18 at 11:26 +0100, Uwe Ligges wrote:
Jessica Higgs wrote:
Sorry to bother everyone, but I've looked in all of the help files and
manuals I have and I can't find the answer to this question. I'm doing
principle component analysis by calculating the eigen vectors of a
Peter Dalgaard wrote:
The models I use for the anovas are the following:
aov(vecData ~ (facWithin + facBetweenROI + facBetweenCond)^2)
aov(vecData ~ facBetweenROI + facBetweenCond %in% facWithin +
Error(facBetweenROI %in% facWithin))
aov(vecData ~ facBetweenCond + facBetweenROI %in% facWithin +
Jari Oksanen wrote:
On Fri, 2005-02-18 at 11:26 +0100, Uwe Ligges wrote:
Jessica Higgs wrote:
Sorry to bother everyone, but I've looked in all of the help files and
manuals I have and I can't find the answer to this question. I'm doing
principle component analysis by calculating the eigen
Gabor Grothendieck wrote:
Michael Grottke Michael.Grottke at duke.edu writes:
: I am currently using R for fitting a model to various data sets
: (minimizing the negative log-likelihood) and calculating a number of
: metrics based on the parameter estimates. Within these calculations, I
: have
Wow, I'm getting confused...The syntax Petr suggested does what I
wanted, but things are stille wrong...Maybe a bug? Let me explain.
I got two vectors:
x = c(3, 3, 3, 4, 3, 4, 3, 4, 3, 4)
y = c(5, 2, 5, 5, 2, 2, 5, 5, 4, 2)
then I do the barplot you suggest
barplot(rbind(table(x), table(y)),
Arne Henningsen wrote:
type ?legend (and please read the posting guide)
I don't think it is that easy, but you have to tweak manually., e.g. by
two calls to legend.
Uwe Ligges
On Friday 18 February 2005 11:11, Haiyong Xu wrote:
Hi there,
I made a plot with histogram and the curve of kernel
On Fri, 18 Feb 2005 13:00:40 +0100 T Petersen wrote:
Wow, I'm getting confused...The syntax Petr suggested does what I
wanted, but things are stille wrong...Maybe a bug? Let me explain.
I got two vectors:
x = c(3, 3, 3, 4, 3, 4, 3, 4, 3, 4)
y = c(5, 2, 5, 5, 2, 2, 5, 5, 4, 2)
then
What you want is probably:
cxy - c(x,y)
xy - rep( c(x,y), c(length(x),length(y)) )
( txy - table(xy, cxy ) )
cxy
xy 2 3 4 5
x 0 6 4 0
y 4 0 1 5
barplot( txy, beside=T )
Bendix Carstensen
--
Bendix Carstensen
Senior Statistician
Steno Diabetes Center
Niels
On 18 Feb 2005 at 13:00, T Petersen wrote:
Wow, I'm getting confused...The syntax Petr suggested does what I
wanted, but things are stille wrong...Maybe a bug? Let me explain.
Bugs are exceptionally rare in R.
I got two vectors:
x = c(3, 3, 3, 4, 3, 4, 3, 4, 3, 4)
y = c(5, 2, 5, 5,
Yeah, that's it. I have to catagorize the data AND tell R how many
catagories there are. It works perfectly now and I've learned some
more:-D Great.
Achim Zeileis wrote:
On Fri, 18 Feb 2005 13:00:40 +0100 T Petersen wrote:
Wow, I'm getting confused...The syntax Petr suggested does what I
Bela Bauer [EMAIL PROTECTED] writes:
Peter Dalgaard wrote:
The models I use for the anovas are the following:
aov(vecData ~ (facWithin + facBetweenROI + facBetweenCond)^2)
aov(vecData ~ facBetweenROI + facBetweenCond %in% facWithin +
Error(facBetweenROI %in% facWithin))
aov(vecData ~
Hi,
I've been up all night trying to get the following to work.
First here is the setup. I have a P4 1G mem running WinXP SP2, R 2.0.1
patched 2005-01-15, MySQL 4.1.7 and MyODBC 3.51.
I've been pulling data from MySQL using the code at the end of the post,
where start.date and end.date are
Hi
I changed you function a little bit, so there is no more conflict
in the if condition:
mecdf-function(u,v,z) {
u=sort(u)
v=sort(v)
n=length(u)
m=length(z)
nb - numeric(m)
for(j in seq(1,m)) {
nb.temp=0
for (i in seq(1,n)) {
if (u[i]z[j] v[i]z[j]) {
Can't seem to find a x86_64 RPM for R on any of the DL mirrors. Does one
exist?
From: Peter Dalgaard p.dalgaard_at_biostat.ku.dk
Date: Fri 22 Oct 2004 - 23:00:41 EST
Prof Brian Ripley [EMAIL PROTECTED] writes:
R does not run under (beta) 64-bit Windows on x86_64 and we have no plans
On Fri, 2005-02-18 at 14:47 +, Dan Bolser wrote:
The following single line of code shows what I am trying to do, and the
problem I am having...
barplot(c(101,102,103),ylim=c(100,103))
The 'xaxis' is missing, and the grey bars 'fall off' the plot area. This
is generally ugly, and I
Dan Bolser wrote:
The following single line of code shows what I am trying to do, and the
problem I am having...
barplot(c(101,102,103),ylim=c(100,103))
The 'xaxis' is missing, and the grey bars 'fall off' the plot area. This
is generally ugly, and I would like to trim the bars (ideally they would
I think a workaround, that will do what you want is:
barplot(c(101,102,103) - 100, offset = 100)
hth,
Z
On Fri, 18 Feb 2005 14:47:24 + (GMT) Dan Bolser wrote:
The following single line of code shows what I am trying to do, and
the problem I am having...
Yes, under redhat/fc3. Did you forget to mention SuSE?
On Fri, 18 Feb 2005, Thomas Colson wrote:
Can't seem to find a x86_64 RPM for R on any of the DL mirrors. Does one
exist?
From: Peter Dalgaard p.dalgaard_at_biostat.ku.dk
Date: Fri 22 Oct 2004 - 23:00:41 EST
Prof Brian Ripley [EMAIL
Yes, I meant to say Suse.
I had tried Fedorabut I'm one of those who has to have bleeding edge
hardware...for which there are no working Fedora Drivers. Hence the switch
to Suse...so I can get video..so I can get a 64 Bit R running.
All of this is just a test. If we can get 64Bit R
Thank for your help
I obtained profiles and I found mosaicplot as an interesting alternative.
I don't like my solution about legend in profiles graphics: I inserted empty
extra columns in order to avoid tue superimposed of legend.
#Data
N - matrix(0,3,6)
N[1,] - c(7,7,5,0,4,4)
N[2,] -
On Fri, 18 Feb 2005 10:50:37 -0500 Campo Elías PARDO wrote:
Thank for your help
I obtained profiles and I found mosaicplot as an interesting
alternative.
I don't like my solution about legend in profiles graphics: I inserted
empty extra columns in order to avoid tue superimposed of
Hello,
I apologize for this question that may has been asked a lot of times
but I could not go through it.
I create a multivariate time series containing NA values.
I want to compute a linear regression and obtain a time serie for both
residuals and fitted values. I have tried the trick
Tom Colson [EMAIL PROTECTED] writes:
Yes, I meant to say Suse.
I had tried Fedorabut I'm one of those who has to have bleeding edge
hardware...for which there are no working Fedora Drivers. Hence the switch
to Suse...so I can get video..so I can get a 64 Bit R running.
All of
hello,
Suppose in Rnw file, I compute a numeric of name x containing the value 1.
In my tex file, I want to write
Let x= the real value of x
so that I can see in my dvi file : Let x = 1,
with 1, the actual value of x written in a math environnement for example.
Thanks,
Matthieu
Here is a generalisation of the function that others have suggested to
take take more than 2 vectors.
my.barplot - function(...){
my.list - list(...)
lev - sort( unique( unlist(my.list) ) )
tmp - t(sapply( my.list, function(v) table(factor(v, levels=lev))) )
barplot(tmp, beside=T)
}
w
I tried Ken's suggestion
read.table(pipe(pbpaste),header=TRUE)
on my Mac OS X system and it worked *without* generating any warning message.
If my experience represents the norm, and Ken's is the exception, it
is so simple that no further contribution to R is needed, I would
say. Thank you,
I believe you want \Sexpr{}
for instance:
let $x = \Sexpr{x}$
or if you need rounding
let $x = \Sexpr{round(x, dig=4)}$
On Fri, 18 Feb 2005, Matthieu Cornec wrote:
hello,
Suppose in Rnw file, I compute a numeric of name x containing the value 1.
In my tex file, I want to write
Let x=
De : [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] la part de
Matthieu Cornec
Envoye : vendredi 18 fevrier 2005 17:40
hello,
Suppose in Rnw file, I compute a numeric of name x
containing the value 1.
In my tex file, I want to write
Let x= the real value of x
so that I can see in my
I'm trying to export a large data frame to a text file for permanent
storage. The only thing I could find was the treeglia Package but that
didn't work. Any suggestions?
Thanks!
Christina D Smith
PhD Student, GRA
Statistics Department
Kansas State University
Don MacQueen [EMAIL PROTECTED] writes:
I tried Ken's suggestion
read.table(pipe(pbpaste),header=TRUE)
on my Mac OS X system and it worked *without* generating any warning message.
If my experience represents the norm, and Ken's is the exception, it
is so simple that no further
In fact, I noticed today that when I copied from an Excell spreadsheet,
rather than just putting some text in a file, that it worked as you
say.
I also downloaded xclip and compiled it, which works just fine
on the Mac, and this mechanisms seems to work the same way as
pbpaste, in terms of
Look at ?write.table.
Also, the data import/export manual on the r-project website is quite
useful.
Sean
On Feb 18, 2005, at 12:32 PM, Christina D Smith wrote:
I'm trying to export a large data frame to a text file for permanent
storage. The only thing I could find was the treeglia Package but
Did you try write.table? If yes, what do you see as its
deficiencies?
spencer graves
Christina D Smith wrote:
I'm trying to export a large data frame to a text file for permanent
storage. The only thing I could find was the treeglia Package but that
didn't work. Any suggestions?
Hello Sander,
That's a good idea and i am up to it.
Right now i am in an exam period, so it's not really the better time,
give me a couple of weeks and i will come up with a specific format of R
files to submit to me that i could post-process to generate html documents.
To my mind, those html
If you add a print(p), you will find that after a few iterations
u is negative which leads to problems with the power. It sometimes help write
u=exp(p), and compute the log later. From a statistical point of view, I am not
always happy with that solution, but even Pinheiro/Bates use it in the
Hi,
I am using the Strucchange package in R to test for structural change in
regression coeffcient. Given a model y = b0 + b1*X + b2*Z, the Fstats test
whether there is a change in both b1 and b2 over a time period.
Is there any way where I can restrict the test to hold b2 constant and test for
values as the function arguments and it still happens at around nine
monthes, or about 270 loops through the for (i in dates) loop or around
500 calls to the ODBC connection. I say around since I can start the
function with the same inputs and it will crash at different months.
Try to boil
Hello,
one way could be to compute the residuals of the regression y=b0 + b2*Z,
let's call them U, and then test the structural change on the model
U=c0+c1*X.
Maybe there's a better way.
Romain.
Le 18.02.2005 20:03, Yen H., Tong a écrit :
Hi,
I am using the Strucchange package in R to test for
On Fri, 18 Feb 2005 11:03:13 -0800 (PST) Yen H., Tong wrote:
Hi,
I am using the Strucchange package in R to test for structural change
in regression coeffcient. Given a model y = b0 + b1*X + b2*Z, the
Fstats test whether there is a change in both b1 and b2 over a time
period.
Is there
On Fri, 18 Feb 2005 20:14:23 +0100 Romain Francois wrote:
Hello,
one way could be to compute the residuals of the regression y=b0 +
b2*Z, let's call them U, and then test the structural change on the
model U=c0+c1*X.
The approach of Andrews (1993, Econometrica) would be preferrable where
~
Request for contact information
I am trying to locate the contact information for the
individuals who oversee compliance in
document/records management.
Any contact information is appreciated.
Sincerely,
Hellman Chica
Le 18.02.2005 20:18, [EMAIL PROTECTED] a écrit :
Please say you forgot to include putting the R code in also.
Obviously !!
Great suggestion. I didn't thought of it ;-)
Romain.
Otherwise we will all be just wistful graphics appreciators, rather than
generators. ;-)
David Reiner
-Original
Hi,
Thanks for all the thoughtful replies. Let me think on this further.
Warm Regards,
Yen
On Fri, 18 Feb 2005, Achim Zeileis wrote:
On Fri, 18 Feb 2005 20:14:23 +0100 Romain Francois wrote:
Hello,
one way could be to compute the residuals of the regression y=b0 +
b2*Z, let's call them U, and
Hello,
I see on the systemfit manual that you can estimate one-equation IV - I have
a variable, and need to test if it's endogeneous, but do not need to
estimate a system.
Does anyone have any examples of this? Do you just run OLS with the
endogenous variable, and then run a Hausmann to
You are right. The warning disappears at exactly five lines of data,
not including the header.
Well, how often do you come across a data.frame with less than 5 rows
and too many covariates to enter by hand?
kk
Quoting Peter Dalgaard [EMAIL PROTECTED]:
Don MacQueen [EMAIL PROTECTED]
Thanks a bunch.
I happened to generate another dataset to try the command you all
provided. my.data$group is factor and so the !my.data$group command
doesn't work but the !with statement works for both situation. So what i
can modify and make the first one work, just curious.
It is of great
Hi
how is it possible to use more than one command when i'm
didn't want use R CMD BATCH for specific reason?
$ echo (x-1:10) | R --vanilla
works
$ echo (x-1:10 ;y-20:30 ;lm(y ~ x)) | R --vanilla
works not.
Is it further possible using bash variables like $i from a loop
in the bash echo call
Hi, All
How does one remove relevant information from a regression output besides
just the coefficients?
I've been able to modify the example given under help(by) to give me some
additional information, but not everything I need.
If you adjust the call statement from what is listed by adding
Le 18.02.2005 22:52, Christian Schulz a écrit :
Hi
how is it possible to use more than one command when i'm
didn't want use R CMD BATCH for specific reason?
$ echo (x-1:10) | R --vanilla
works
$ echo (x-1:10 ;y-20:30 ;lm(y ~ x)) | R --vanilla
works not.
The following works for me:
echo x-1:10
Christian Schulz [EMAIL PROTECTED] writes:
Hi
how is it possible to use more than one command when i'm
didn't want use R CMD BATCH for specific reason?
$ echo (x-1:10) | R --vanilla
works
$ echo (x-1:10 ;y-20:30 ;lm(y ~ x)) | R --vanilla
works not.
It would probably help to use
Hi, there:
I am always experiencing the scalability of some R packages. This
time, I am trying gbm to do adaboosting on my project. Initially I
tried to grow trees by using rpart on a dataset with 200 variables and
30,000 observations. Now, I am thinking if I can apply adaboosting on
it.
I am
Hi, List,
I am using the package 'gee' downloaded from CRAN several days ago. I
tried to
do a 2 degree freedom contrast but couldn't get any result. It must be so
obvious but I just couldn't get it. Any hint would be greatly appreciated.
Here
is a sample code:
set.seed(123)
mydf -
One way to run multiple R commands within a bash script is with a here
document. See http://www.tldp.org/LDP/abs/html/here-docs.html
Here is an excerpt of a bash script showing its use -- notice that several
bash variables are referenced within it:
#!/bin/bash
.
.
R
I am always experiencing the scalability of some R packages. This
time, I am trying gbm to do adaboosting on my project. Initially I
tried to grow trees by using rpart on a dataset with 200 variables and
30,000 observations. Now, I am thinking if I can apply adaboosting on
it.
R seems to be
echo x-1:10 ;y-21:30 ;lm(y ~ x) | R --vanilla
..uups counting is sometimes difficult, or to late :-( , but many
thanks for this link and example.
regards, christian
Pierre Kleiber wrote:
One way to run multiple R commands within a bash script is with a
here document. See
I'm using R 2.0.1 under windows XP. I'd like to produce an xyplot with
lattice, in which the x axis shows normally (with tics and numbers), but
there are neither tics nor numbers for y. (I'm using layout=c(1,10),
and ylab=.)
From the html help for xyplot, it appears I need to use the scales
On Friday 18 February 2005 18:03, David Parkhurst wrote:
I'm using R 2.0.1 under windows XP. I'd like to produce an xyplot
with lattice, in which the x axis shows normally (with tics and
numbers), but there are neither tics nor numbers for y. (I'm using
layout=c(1,10), and ylab=.)
From
So the help for loadURL says:
'loadURL' is a convenience wrapper which downloads a file, loads
it and deletes the downloaded copy.
Trying to load an rda file on Windows (XP, R-devel) I was surprised
when I received an error about input being corrupted with LF
replaced by CR.
The fix
Matthieu Cornec matthieu.cornec at gmail.com writes:
I create a multivariate time series containing NA values.
I want to compute a linear regression and obtain a time serie for both
residuals and fitted values. I have tried the trick ts.intersect,
without success.
Could you help me out of
Sander Oom slist at oomvanlieshout.net writes:
:
: Dear R users,
:
: Following some of the recent questions and discussions about the R
: plotting abilities, it occurred to me again that it would be very
: valuable to have an R graph gallery.
:
: Eric Lecoutre made a very nice example in:
:
Howdy
What I 'd like to analyze with a large data on building permits is to find
time series effect of urban policy on buildings as well as
cross-sectional effects in any. In 1990 the specialZone urban policy
was introduced. I guess that the effects of this specialZone policy
would be different
On Fri, 18 Feb 2005, Seth Falcon wrote:
So the help for loadURL says:
'loadURL' is a convenience wrapper which downloads a file, loads
it and deletes the downloaded copy.
Trying to load an rda file on Windows (XP, R-devel) I was surprised
when I received an error about input being
A bit more explanation.
On Sat, 19 Feb 2005, Prof Brian Ripley wrote:
On Fri, 18 Feb 2005, Seth Falcon wrote:
So the help for loadURL says:
'loadURL' is a convenience wrapper which downloads a file, loads
it and deletes the downloaded copy.
Trying to load an rda file on Windows (XP,
72 matches
Mail list logo