The new package benchden 1.0.0 implements 28 benchmark densities for
nonparametric density estimation that were introduced by A. Berlinet and
L. Devroye (A Comparison of Kernel Density Estimates, Pub. Inst. Stat.
Univ. Paris, XXXVIII, fasc. 3, 1994, 3-59,
http://cg.scs.carleton.ca/~luc/devs.html
Dear R-users,
I'm using Ubuntu dapper, which only have R of Version 2.2.1.
Would anybody tell me how to install the latest version of R with
Synaptic in Ubuntu dapper system.
Thanks!
__
R-help@stat.math.ethz.ch mailing list
David Duffy wrote:
Waverley [EMAIL PROTECTED] asked:
Dear Colleagues,
I am looking for a package or previous implemented R to subgroup and
exaustively divide a vector of squence into 2 groups.
--
Waverley @ Palo Alto
Google [R] Generating all possible partitions and you will find
I use something like Gavin's solution for functions which are not used too
often. The problem with using 'source' is that the user environment gets
cluttered.
I 'save' the most useful functions to a single file (MMmisc.Rda), put it
in the HOMEPATH directory (use Sys.getenv(HOMEPATH) to find
Hi Markus,
You can't assume that a typical R users knows much about S+.
R has been beyond S+ for a long time
{{ :-) :-) please Insightful staff, don't start to jump at me !}}
Even I, as a very long time S and Splus user (of the past:
1987--~1997), have never, I think, used align().
Can you
Hi,
Until now, I thought that the results of glm() and bigglm() would
coincide. Probably a naive assumption?
Anyways, I've been using bigglm() on some datasets I have available.
One of the sets has 15M observations.
I have 3 continuous predictors (A, B, C) and a binary outcome (Y).
And
I'm using Ubuntu dapper, which only have R of Version 2.2.1.
Would anybody tell me how to install the latest version of R with
from the CRAN Ubuntu readme- works for synaptic as well:
* UBUNTU
R packages for Ubuntu on i386 are available. The plans are to support at
least the latest Ubuntu
One of your home directories on Windows is %HOMEDRIVE%%HOMEPATH% (you do
need to give the drive), but only one: see the rw-FAQ.
Reading ?file.path will help you not reinvent the wheel.
So I think attach(path.expand(~/MMmisc.rda) is far more portable (as
well as much more readable).
On Thu, 28
On Fri, 29 Jun 2007, Martin Maechler wrote:
Hi Markus,
You can't assume that a typical R users knows much about S+.
R has been beyond S+ for a long time
{{ :-) :-) please Insightful staff, don't start to jump at me !}}
Even I, as a very long time S and Splus user (of the past:
As embedFonts creates a new file, the bounding box of the original one is
not relevant. (Yes, outfile = file by default, but it is still a new
file.)
I guess the switches
-dDEVICEWIDTHPOINTS=w -dDEVICEHEIGHTPOINTS=h
might help to create the new file with the bounding box you want.
On
Hello,
I would like to have some information about acf with missing values.
Let us consider this example:
x=rnorm(100)
x2=x
x2[sample(100,10)]=NA
acf1=acf(x)
acf2=acf(x2,na.action=na.pass)
The computation of the acf is different for the two data sets. Looking
at the the code reveals that with
Hi,
I've been using R for a few weeks now, but consider myself still a
newbie, especially in what concerns the basics of data handling in R.
My situation is this:
I read in data from a database using RODBC, and then use table to
produce a table of counts per years, table which I give to
Hello!
There were some questions regarding warning messages in Design library,
but no answer how to fix them. What about:
use of storage.mode(x) - single is deprecated: use mode- instead
What does it mean? How to use properly simple model like:
m1 = ols(Y ~ A + B + C, data = someData)
After
z - read.table(clipboard)
z
V1 V2
1 1990 20
2 1991 15
3 1995 17
4 1997 9
5 1998 10
6 1999 11
7 2000 5
zz - merge(data.frame(V1=1990:2000), z, by=V1, all.x=T)
plot(zz, type=l)
Jacques VESLOT
INRA - Biostatistique Processus Spatiaux
Site Agroparc 84914 Avignon Cedex 9, France
Tel:
Hi
From help page
A data frame is a list of variables of the same length with unique row
names, given class data.frame.
so something completely different from matrix (which is AFAIK a vector
with dimensions attribute). Therefore matrix needs to have all its values
of the same type
Thanks a lot! Wow, I know why I love R, things are so incredibly easy
with R (once you know how ;-) )
Moreover I've found messages in the archive showing how to make plot
draw as many ticks as I've got years, so everything is OK.
Thanks for the help,
Anne-Marie
Quoting Jacques VESLOT
Hello,
I am a Mac user and prefer the quartz device. So far, I have always
typed the following in manually after starting R via ESS:
library(CarbonEL)
options(device=quartz)
That works without problems, and allows me to use the quartz device
instead of X11.
I put this into my .Rprofile,
Dietrich Trenkler wrote:
Dear HelpeRs,
I'm very fond of Sweave and I use it as often as possible. It'a a pity
I can't use it for larger projects or can I?
For instance suppose I have three files file1.rnw, file2.rnw and
file3.rnw with Sweave code. Working on file2.rnw I whould like to
Dear HelpeRs,
I'm very fond of Sweave and I use it as often as possible. It'a a pity
I can't use it for larger projects or can I?
For instance suppose I have three files file1.rnw, file2.rnw and
file3.rnw with Sweave code. Working on file2.rnw I whould like to
exclude file1.rnw and file3.rnw
Tobias Verbeke wrote:
Dietrich Trenkler wrote:
Dear HelpeRs,
I'm very fond of Sweave and I use it as often as possible. It'a a pity
I can't use it for larger projects or can I?
For instance suppose I have three files file1.rnw, file2.rnw and
file3.rnw with Sweave code. Working on
Birgit Lemcke wrote:
Hello,
(Power Book G4, Mac OS X, R 2.5.0)
I would like to repeat the function range for 85 Vectors (V1-V85).
I tried with this code:
i-0
repeat {
+ i-i+1
+ if (i85) next
+ range (Vi, na.rm = TRUE)
+ if (i==85) break
+ }
I presume that the Vi is wrong,
Sorry folks I posted the code with a bug in approach 2. aarrrhh. it should have
been...
## Approach 2: loop on k2
output2 = matrix(0,nrow=n,ncol=k2)
pt2 = proc.time(for (i in 1:k2) output2[,i] = rowSums( m1*(m2[,rep(i,3)]) ))
I haven't seen any other response yet (after 8 hours!) but doesn't:
--- Stephen Tucker [EMAIL PROTECTED] wrote:
Dear John,
Perhaps I am mistaken in what you are trying to
accomplish but it seems like
what is required is that you call lstfun() outside
of ukn(). [and remove the
call to lstfun() in ukn()].
nts - lstfun(myfile, aa, bb)
results - ukn(dd1,
Hello Jim,
thanks for your answer. At the moment I am using this code:
Range0-sapply(1:85, function(i) eval(parse(text=paste(range(V, i,
, na.rm=T), sep=
and it works really fine.
The code you sent me is also fine but how can I implement, that
missing values are TRUE?
Thanks a lot for
--- Jason Barnhart [EMAIL PROTECTED] wrote:
The problem isn't the function call.
First, list1 returned by lstfun does not name its
elements so nts$cda
won't work. See code change in lstfun.
Oh, I see. I missed this completely. I clearly was a
bit groggy yesterday afternoon.
Hi,
model1-aov(dv~iv.1*iv.2*iv.3)
mod.av - anova(model1)
names(mod.av)
mod.av$Df
mod.av$Mean
On 29/06/07, Taka Matzmoto [EMAIL PROTECTED] wrote:
Dear R users,
I would like to extract df and Mean Sq values. I tried several things (e.g
.,
str(model1), names(model1)) but I can't find a way to
I have a process that generates distributions that look like normal,
but with fat tails. I would like to model them as if they were
a mix of two normals (with zero mean). Is there any function that
recovers the standard deviations and the probability based on a
sample?
I would like to generate
On 6/29/07, Birgit Lemcke [EMAIL PROTECTED] wrote:
Hello Jim,
thanks for your answer. At the moment I am using this code:
Range0-sapply(1:85, function(i) eval(parse(text=paste(range(V, i,
, na.rm=T), sep=
It is a matter of taste, but I tend to prefer:
a - list()
for (i in 1:85)
All of my resources for numerical analysis show that the spectral
decomposition is
A = CBC'
Where C are the eigenvectors and B is a diagonal matrix of eigen values.
Now, using the eigen function in R
# Original matrix
aa - matrix(c(1,-1,-1,1), ncol=2)
ss - eigen(aa)
# This results yields back
EOF from a keyboard on Windows is often Ctrl+Z.
But you're right; it's platform dependent. CtrlZ in Unix has less desirable
effects on readLines(). And on your running R process...
Drat.
Peter Dalgaard [EMAIL PROTECTED] 29/06/2007 12:42:41
S Ellison wrote:
Wouldn't it be nice if the Help
Thanks very much. A very nice solution. The
environment problem was the result of one last
deperate try when the actual problem as Jason pointed
out was that I was not naming my list elements and
thought that I had.
This looks like it will work quite nicely. I am pretty
sure that there is a
--- Jason Barnhart [EMAIL PROTECTED] wrote:
The problem isn't the function call.
First, list1 returned by lstfun does not name its
elements so nts$cda
won't work. See code change in lstfun.
I missed that entirely. I was groggier than I
realised yesterday afternoon. I had at least once
Bingshan Li wrote:
Hi All,
Now it works. Thanks for all your answers and the explanations are
very clear.
Bingshan
But note that you are not using R correctly unless you are doing a
simulation and have some special speed issues. Let the model functions
do all this for you.
Frank
Petar Milin wrote:
Hello!
There were some questions regarding warning messages in Design library,
but no answer how to fix them. What about:
use of storage.mode(x) - single is deprecated: use mode- instead
What does it mean? How to use properly simple model like:
m1 = ols(Y ~ A + B +
Thank you for your responses, I should have given an example of the
functionality I am looking for, here are three typical scenarios that
I deal with a lot in my work:
- a regular timeseries with lots of missing values that I want to
convert to the corresponding regular time series with mssing
For a general square matrix A, the eigenvalue decomposition is
A = CBC^{-1}
For the special case of symmetric A,
C^{-1} = C'
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
Hi, I have a series of return data, a and b are factors. I would like to
build a matrix which contains each vector of returns. I am thinking about
something as following, but I guess there should be a sensible way of doing
this.
returns - split(return, list(regimef, assetf))
cbind(returns[[1]],
On 29-Jun-07 13:23:05, Ted Harding wrote:
[Sorry -- a silly typo in my previous]:
If A is not symmetric, you have left eigenvectors:
x'*A = lambda*x'
and right eigenvectors:
A*x = lambda*x
and the left eigenvectors are not the same as the right
eigenvectors, though you have the
On 29-Jun-07 12:29:31, Doran, Harold wrote:
All of my resources for numerical analysis show that the spectral
decomposition is
A = CBC'
Where C are the eigenvectors and B is a diagonal matrix of eigen
values. Now, using the eigen function in R
# Original matrix
aa -
livia wrote:
Hi, I have a series of return data, a and b are factors. I would like to
build a matrix which contains each vector of returns. I am thinking about
something as following, but I guess there should be a sensible way of doing
this.
returns - split(return, list(regimef, assetf))
why don't you use a 'list' as the return value. The 'cbind' is going to
assume that each of the 'return[[..]]' have the same length or you are going
to get error messages:
cbind(1:3,4:10)
[,1] [,2]
[1,]14
[2,]25
[3,]36
[4,]17
[5,]28
[6,]39
On Fri, 29 Jun 2007, Markus Loecher wrote:
Thank you for your responses, I should have given an example of the
functionality I am looking for, here are three typical scenarios that I deal
with a lot in my work:
- a regular timeseries with lots of missing values that I want to convert to
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hi alls,
i have to code a family of bar charts. After reading the doc, i cannot
understand if it is possible to shade the bar colors and how.
With shading i don't mean `density`. I mean something like that:
Dear all,
I am fitting a generalized additive model with several discrete and continuous
predictors, using the library mgcv.
Basically, I have two questions:
1.
If I model the response variable y with f(x), z and f(x):z, where f(x) has 1
edf and f(x):z has 4 edf, can I model x parametrically,
Benilton Carvalho wrote:
Hi,
Until now, I thought that the results of glm() and bigglm() would
coincide. Probably a naive assumption?
Anyways, I've been using bigglm() on some datasets I have available.
One of the sets has 15M observations.
I have 3 continuous predictors (A, B, C) and
Hi Peter,
thank you very much for your feedback.
As for your observations, I do realize that I'm using 1.5 chunks for
this particular case (10e6 gives around 8 chunks on other sets).
I just noticed that I didn't add the difference in the deviances that
I observed:
m1$deviance-m2$deviance
comments in line
shirley zhang wrote:
Hi Simon,
Thanks for your reply. Your reply reminds me that book. I've read it
long time ago, but haven't try the weights option in my projects
yet:)
Is the heteroscedastic test always less powerful because we have to
estimate the within group
Hi,
I 'd like to match each member of a list to a target string, e.g.
--
mylist=c(MN,NY,FL)
g=regexpr(mylist[1], Those from MN:)
if (g0)
{
On list
}
--
My question is:
How to add an end-of-string symbol '$' to the to-match string? so that
Hi Frank,
I do not quite get you. What do you mean by simulation and speed issues? I do
not see why they have to be considered in logistic regression.
Thanks.
Bingshan
From: Frank E Harrell Jr [mailto:[EMAIL PROTECTED]
Sent: Fri 6/29/2007 7:40 AM
To: Li,
Hi Dietrich,
I am writing my thesis, made up of several papers that have been
expanded into chapters. Each chapter was a .tex file until I started
using Sweave.
Now each chapter is an .Rnw file. My master LaTeX document has this:
\include{introduction}
\include{epidemiology}
\include{report}
mylist=c(MN,NY,FL)
g=regexpr(paste(mylist[1], $, sep=), Those from MN:)
if (g0)
{
On list
}
or in a loop
for (i in mylist){
if (regexpr(paste(mylist[i], $, sep=)) 0){
.code for those from
}
}
On 6/29/07, runner [EMAIL PROTECTED] wrote:
Hi,
I 'd like to match each
Li, Bingshan wrote:
Hi Frank,
I do not quite get you. What do you mean by simulation and speed issues? I do
not see why they have to be considered in logistic regression.
Exactly. So don't use techniques that are only needed when such issues
do have to be considered.
Thanks.
Hello,
I have a GAM plot in 3D which was generated from the mgcv package
(plot.gam) which seems to call the persp( ) function from graphics.
This plot is one of three being plotted in the graphics window to copy
to a manuscript. The plot's rotation has been set to clearly show the
response
Dear,
I'm not getting Installing packages:
install.packages(c(exactRankTests))
trying URL `http://cran.r-project.org/bin/windows/contrib/2.0/PACKAGES'
Content type `text/plain' length 26129 bytes
opened URL
downloaded 25Kb
trying URL `http://cran.r-
The first question you should ask yourself (and really think about the
answer) is Why do I want to do this?
Fancy colors and shadings can detract from a plot rather than enhance
it. The wrong choice of colors can make bars look bigger or smaller
than they really are. Reading Tufte's The visual
require(exactRankTests)
--
Henrique Dallazuanna
Curitiba-Paraná-Brasil
25° 25' 40 S 49° 16' 22 O
On 29/06/07, Marcus Vinicius [EMAIL PROTECTED] wrote:
Dear,
I'm not getting Installing packages:
install.packages(c(exactRankTests))
trying URL
I think you are looking for paste().
And you can replace your for loop with lapply(), which will apply regexpr to
every element of 'mylist' (as the first argument, which is 'pattern'). 'text'
can be a vector also:
mylist - c(MN,NY,FL)
lapply(paste(mylist,$,sep=),regexpr,text=Those from MN:)
First let me admit that I am no statistician... rather, an ecologist with
just enough statistical knowledge to be dangerous.
I've got a dataset with percent ground cover values for species and other
entities. The data are left censored at zero, in that percent ground cover
cannot be negative.
Dear UseRs called Hadley, or Paul,
I am trying to print an edited ggplot2/grid graphics to a metafile. With the
commented line below it works, but when I edit the plot by uncommenting the
line, it fails, because it's illegal to have 2 graphics in a metafile. It
works with pdf, but even then I get
I have a dataframe called hawk. Source file looks ok. read.table seems
ok. Can view using R editor. Again looks fine.
Now, I am new to windows version of R. When I type in 'hawk' under
Linux, I expect to see the rows listed. That isn't happening, as shown
below.
attach(hawk)
hawk
Error in
Marcus Vinicius wrote:
Dear,
I'm not getting Installing packages:
install.packages(c(exactRankTests))
trying URL `http://cran.r-project.org/bin/windows/contrib/2.0/PACKAGES'
Content type `text/plain' length 26129 bytes
opened URL
downloaded 25Kb
This means you are using R-2.0.x?
Roy Wilson wrote:
I have a dataframe called hawk. Source file looks ok. read.table seems
ok. Can view using R editor. Again looks fine.
Now, I am new to windows version of R. When I type in 'hawk' under
Linux, I expect to see the rows listed. That isn't happening, as shown
below.
Dear R users Experts,
This is just a curiousity, I was wondering why the dominant eigenvetor and
eigenvalue
of the following matrix is given as the third. I guess this could complicate
automatic selection
procedures.
000005
100000
0100
There is no dominant eigenvalue: The eigenvalues of that matrix
are the 6 different roots of 5. All have modulus (or absolute value) =
1.307660. When I raised them all to the 6th power, all 6 were 5+0i.
Someone else can tell us why this is, but this should suffice as
an initial
Marco Visser wrote:
Dear R users Experts,
This is just a curiousity, I was wondering why the dominant eigenvetor and
eigenvalue
of the following matrix is given as the third. I guess this could complicate
automatic selection
procedures.
000005
1000
On Fri, 29 Jun 2007, Peter Dalgaard wrote:
David Duffy wrote:
Waverley [EMAIL PROTECTED] asked:
Dear Colleagues,
I am looking for a package or previous implemented R to subgroup and
exaustively divide a vector of squence into 2 groups.
--
Waverley @ Palo Alto
Google [R]
[SNIP]
This has been very helpful though I still do not
understand why one must call nts$cda using the
eval(parse()) command. Is it because nts is created
within the ukn environment?
You don't *have* to use the eval(parse()). This works just as
well: mysum - nts$cda.
However, it
On 29-Jun-07 21:09:37, Peter Dalgaard wrote:
Marco Visser wrote:
This is just a curiousity, I was wondering why the dominant
eigenvetor and eigenvalue of the following matrix is given
as the third. I guess this could complicate automatic selection
procedures.
000005
1
David Duffy wrote:
On Fri, 29 Jun 2007, Peter Dalgaard wrote:
David Duffy wrote:
Waverley [EMAIL PROTECTED] asked:
Dear Colleagues,
I am looking for a package or previous implemented R to subgroup and
exaustively divide a vector of squence into 2 groups.
--
Waverley @ Palo
Marco Visser wrote:
Dear R users Experts,
This is just a curiousity, I was wondering why the dominant
eigenvetor and
eigenvalue
of the following matrix is given as the third. I guess this could
complicate
automatic selection
procedures.
Comment: In Matlab the the
I would like to know how I can assign a name to a name. I have a
dataset that has different years in it. I am writing scripts using R
and I would like to give a month a generic name and then use the generic
name to do different analysis. The reason for the generic name would be
so that I only
Dear R users;
Is there any package or function that I can use to perform LOOCV with
prcomp? Basically I want to use that approach to get an idea of the
optimal number of PC.
Thanks for any idea
PM
__
R-help@stat.math.ethz.ch mailing list
Hi,
Is there a way to get the scale parameter for the gamma link in the gee
package? I know that object$scale gives the dispersion parameter, but I'm
looking for the scale parameter, similar to what gamma.shape() or
gamma.dispersion() gives in glm(). Thanks
Patrick
[[alternative HTML
Hello, all
I am trying to install RGTK2 on my Ubuntu 7.04 system. The installation
fails with a message that RGtk2 requires GTK 2.8. As far as I can tell I
have GTK+ 2.10.11 installed. Can anyone suggest a way to proceed?
Thanks very much.
Here is the failed installation:
On Fri, 2007-06-29 at 23:11 -0400, Andrew Muller wrote:
Hello, all
I am trying to install RGTK2 on my Ubuntu 7.04 system. The installation
fails with a message that RGtk2 requires GTK 2.8. As far as I can tell I
have GTK+ 2.10.11 installed. Can anyone suggest a way to proceed?
Thanks
On 29 June 2007 at 23:11, Andrew Muller wrote:
| I am trying to install RGTK2 on my Ubuntu 7.04 system. The installation
| fails with a message that RGtk2 requires GTK 2.8. As far as I can tell I
| have GTK+ 2.10.11 installed. Can anyone suggest a way to proceed?
Something is not right in your
Hi
I work with package rpart for draw trees,for example:
library(rpart)
fit - rpart(Price ~ Mileage + Type + Country, cu.summary)
plot(fit, compress=TRUE)
text(fit, use.n=TRUE)
and then i want compute error of each tree with t.test.(with package ROCR
comparison two trees).
and i
You can just create another variable which contains the names you want:
## let
Year - c(rep(1999,2),rep(2000,2),rep(2001,3))
## one alternative
getYearCode1 - function(yr) {
# yr can be a vector
ifelse(yr==1999,Year1,
ifelse(yr==2000,Year2,
ifelse(yr==2001,Year3)))
78 matches
Mail list logo