Dear Mike
Mike Cheung writes:
Dear List,
I have some discrete data and want to calculate the percentiles and the
percentile ranks for each of the unique scores. I can calculate the
percentiles with quantile().
I know that ecdf can be used to calculate the empirical cumulative
Patrick Drechsler wrote:
Hi,
I was wondering if it's possible to have fonts in plots to be
autoscaled to the same font size used by LaTeX in a surrounding
Sweave document.
See ?strwidth which might help for the required calculations.
Uwe Ligges
Here's a short example in which the fonts of the
Mike Cheung [EMAIL PROTECTED] writes:
I know that ecdf can be used to calculate the empirical cumulative
distribution. However, I don't know how to exact the cumulative
probabilities for each unique element. The requirement is similar to
the FREQUENCIES in SPSS. Could someone help me in
Mulholland, Tom [EMAIL PROTECTED] writes:
tdata
[,1] [,2] [,3] [,4] [,5]
[1,]010 -1 -1
[2,]200 -5 -6
[3,]003 -5 -6
[4,]1 -1 -100
sumtd
[1] 0 0 0 -2
which I can calculate to give me 3x+30, x+12, 2x+20, 12x, x
Hello,
I've tried stl decomposition but I made a mistake
I want to make a calibration on a sample, in french we called it
Redressement d'un échantillon
Thank u
[[alternative HTML version deleted]]
__
R-help@stat.math.ethz.ch mailing
On Thu, 06 Jan 2005 23:56:31 +0100,
Patrick Drechsler (PD) wrote:
Hi,
I was wondering if it's possible to have fonts in plots to be
autoscaled to the same font size used by LaTeX in a surrounding
Sweave document.
Not using the standard mechanism, because there figures are rescaled
Hi,
I want to use hist with non-equi-spaced breaks, picked such that the
fraction of the data points falling in the cells (defined by 'breaks') is
roughly equal accross all cells.
Is there such a function that will automatically try to determine the
breaks to fullfill this requirement?
Hi
has anyone coded up domain colouring for visualizing complex analytic
functions
(such as elliptic functions)?
[
the idea is to depict a complex function f(z) using a filled.contour()
variant
in which the hue is given by Arg(f(z)), and the saturation by Mod(f(z)).
]
--
Robin Hankin
how about:
x - rnorm(400)
nbin-7
hist(x,breaks=quantile(x,prob=seq(0,1,length=nbin+1)))
Bendix Carstensen
--
Bendix Carstensen
Senior Statistician
Steno Diabetes Center
Niels Steensens Vej 2
DK-2820 Gentofte
Denmark
tel: +45 44 43 87 38
mob: +45 30 75 87 38
fax: +45 44 43 07
On Fri, 7 Jan 2005, Dan Bolser wrote:
Hi,
I want to use hist with non-equi-spaced breaks, picked such that the
fraction of the data points falling in the cells (defined by 'breaks') is
roughly equal accross all cells.
Is there such a function that will automatically try to determine the
Dan Bolser [EMAIL PROTECTED] writes:
Hi,
I want to use hist with non-equi-spaced breaks, picked such that the
fraction of the data points falling in the cells (defined by 'breaks') is
roughly equal accross all cells.
Is there such a function that will automatically try to determine the
On Fri, 7 Jan 2005, Dan Bolser wrote:
Hi,
I want to use hist with non-equi-spaced breaks, picked such that the
fraction of the data points falling in the cells (defined by 'breaks') is
roughly equal accross all cells.
?quantile
Is there such a function that will automatically try to
Hi!
I 've a problem to have a lognorm distribution with
mean=1 and var (or sigma)=1.
rlnorm(1000,0,0)
rlnorm(1000,1,1)
rlnorm(1000,0,1)
?
Can you help me?
__
R-help@stat.math.ethz.ch mailing list
On Fri, 7 Jan 2005, BXC (Bendix Carstensen) wrote:
how about:
x - rnorm(400)
nbin-7
hist(x,breaks=quantile(x,prob=seq(0,1,length=nbin+1)))
Thanks for the replies! Quantiles are my new friend. Its true the example
I gave was a bit tricky, I just wanted to get the idea over.
One thing that is
On 07-Jan-05 NDIKUMAGENGE Alice wrote:
Hello,
I've tried stl decomposition but I made a mistake
I want to make a calibration on a sample, in french we called it
Redressement d'un échantillon
Thank u
Are you referring to the sort of thing decsribed, for example, in
args(rlnorm)
function (n, meanlog = 0, sdlog = 1)
NULL
Frederic renaud wrote:
Hi!
I 've a problem to have a lognorm distribution with
mean=1 and var (or sigma)=1.
rlnorm(1000,0,0)
rlnorm(1000,1,1)
rlnorm(1000,0,1)
?
Can you help me?
On Fri, 7 Jan 2005, Dan Bolser wrote:
On Fri, 7 Jan 2005, BXC (Bendix Carstensen) wrote:
how about:
x - rnorm(400)
nbin-7
hist(x,breaks=quantile(x,prob=seq(0,1,length=nbin+1)))
Thanks for the replies! Quantiles are my new friend. Its true the example
I gave was a bit tricky, I just
Dan Bolser [EMAIL PROTECTED] writes:
y - table(cut(x,breaks=quantile(x,seq(0,1,length=nbin+1
y
[1] 399
I only get 399 counts out, and I put 400 counts in?
Look at the include.lowest argument. For some reason this is TRUE in
hist() but FALSE in cut().
--
O__ Peter Dalgaard
I have an S4 class with a slot of class array, and in upgrading to 2.0.1
(from 1.9.1) I have encountered a change in behaviour. This causes me some
difficulties if I want to allow 2-dimensional arrays in the slot.
The following (in 2.0.1) illustrates the point:
Hello everybody,
I'm studying descriptive statistics with R and I want to know how to
calculate the asymmetry and kurtosis coefficients of a sample using R. I'll
appreciate some help.
Thanx,
Talita Perciano Costa Leite
Graduanda em Ciência da Computação
Universidade Federal de Alagoas - UFAL
Hello everybody,
I'm studying descriptive statistics with R and I want to know how to
calculate the asymmetry and kurtosis coefficients of a sample using R. I
would appreciate some help.
Thanx,
Talita Perciano Costa Leite
Graduanda em Ciência da Computação
Universidade Federal de Alagoas - UFAL
On Wednesday 05 January 2005 16:29, Thomas Petzoldt wrote:
Douglas Bates wrote:
I'm not sure what model you want to fit here. To specify a random
effect in lme you need both a grouping factor and a model matrix. The
error message indicates that lme is unable to determine a grouping
On 07-Jan-05 Frederic renaud wrote:
Hi!
I 've a problem to have a lognorm distribution with
mean=1 and var (or sigma)=1.
rlnorm(1000,0,0)
rlnorm(1000,1,1)
rlnorm(1000,0,1)
?
Can you help me?
Not sure what your problem is.
For rlnorm(1000,0,0), you will get
[Sorry for the re-post; my examples got garbled in the original cut/paste.]
Here is a problem that perhaps someone out here has an idea about. It
vaguely reminds me of something
I've seen before, but can't place. Can anyone help?
For multiple imputation, there are simpler methods available if
On Fri, 07 Jan 2005 12:28:04 +
Talita Leite [EMAIL PROTECTED] wrote:
Hello everybody,
I'm studying descriptive statistics with R and I want to know how to
calculate the asymmetry and kurtosis coefficients of a sample using R. I'll
appreciate some help.
install.packages(e1071)
Hi List,
I'm trying to build R-2.0.1 on and AMD64/Linux (Suse 9.1) and I get the
following error while running the configure script.
...
checking for dummy main to link with Fortran libraries... none
checking for Fortran name-mangling scheme... lower case, underscore, extra
underscore
checking
Hi,
I am considering whether or not to buy an apple mac. I have noticed on
one of the R FAQs for Mac OS X that you cannot install packages from
other OS's if C++ code is contained. My question is: Is it possible to
build the package sources containing C++ code on the Mac and then
install them?
Giles Heywood wrote:
I have an S4 class with a slot of class array, and in upgrading to 2.0.1
(from 1.9.1) I have encountered a change in behaviour. This causes me some
difficulties if I want to allow 2-dimensional arrays in the slot.
The following (in 2.0.1) illustrates the point:
Hi!
I'm trying to do some ploytomous logistic regression using multinom() in the
nnet package, but am a bit confused about interpretation of the results
Is it possible to get the following quantities:
I: maximum likelihood estimates to test for fit of model and significance of
each predictor
Thanks to the help I have received from Uwe and Dimitris I have been
able to simulate the data as a list rather than separate objects and
structure in the long format. For the most part, all of my code is
working properly. There is one issue that I can't resolve.
When I do the following all seems
I am analysing data with a dependent variable of insect
counts, a fixed effect of site and two random effects, day,
which is the same set of 10 days for each site, and then
transect, which is nested within site (5 each).
And what exactly are you interested in? Just the differences between
hi Sam,
Building source packages with C++ source code is no problem at all on
Mac OS X if you simply follow the instructions in the FAQ.
best and good luck with your new Mac,
from a content MAC user, best, ingmar
On 1/7/05 2:45 PM, Samuel Kemp [EMAIL PROTECTED] wrote:
Hi,
I am considering
Hi Robin
here's the C++ code (scale already coded)
! it was done under C++ builder and I seem to remember that RGB is in fact
coded as BGR (I've done that a year ago and already forgotten all about it,
roll the years!)
the scale was generated from another C++ program (which I do not find for
On Fri, 7 Jan 2005, Sivakumar Ramagopal wrote:
I'm trying to build R-2.0.1 on and AMD64/Linux (Suse 9.1) and I get the
following error while running the configure script.
...
checking for dummy main to link with Fortran libraries... none
checking for Fortran name-mangling scheme... lower case,
On 06-Jan-05 Michael Friendly wrote:
Here is a problem that perhaps someone out here has an idea
about. It vaguely reminds me of something I've seen before,
but can't place. Can anyone help?
For multiple imputation, there are simpler methods available
if the patterns of missing data are
Thank u !
I will have a look at it!
Message d'origine
De: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]
Date: ven. 07/01/2005 12:21
À: NDIKUMAGENGE Alice
Cc: r-help@stat.math.ethz.ch
Objet: RE: [R] Help for calibration
Hi
The problem is clearly associated to R.2.0:
Same command on same data with same package (RSvgDevice 0.5.3) but with R1.9.1
or R2.0.0 gave me different results: svg files are correct with R1.9.1, not
with R.2.0.0.
(email forward to the package developper)
On Thursday 06 January 2005 15:37,
Dear Tom,
I'm not sure that I follow the question correctly, but I think that you want
to solve the over determined system tdata %*% x == sumtd.
Some time ago, I believe that I posted to the list a function for Gaussian
elimination that I use in teaching basic linear algebra. Here's an updated
I use R on Mac OS X and always install packages from Source. Never had
a problem with that. Not sure if it matters, but I also have Fink
installed as well as the Developers package that comes free with OS X,
so all the various compilers are there.
It's not diffiicult at all, and the OS X
Dear all,
I have a data frame that looks like this:
c1 c2 c3
ABC
BCA
AAB
and so on;
I´d like to produce one single vector consisting of the columns c1,c2,
c3, such that
vector=(A,B,A,B,C,A,C,A,B)
I guess it´s easy to do but I don´t know how...Can anyone help me?
Dear Anne,
There's an anova() method for multinom objects that will allow you to get
likelihood-ratio tests. Likewise, the Anova() function in the car package
has a method for multinom objects.
As to plotting, I have a paper, coauthored with Bob Andersen, on producing
effect plots (partial
Michael Friendly [EMAIL PROTECTED] writes:
[Sorry for the re-post; my examples got garbled in the original cut/paste.]
I don't know about then but they sure are now!
Here is a problem that perhaps someone out here has an idea about. It
vaguely reminds me of something
I've seen before, but
Sivakumar Ramagopal [EMAIL PROTECTED] writes:
Hi List,
I'm trying to build R-2.0.1 on and AMD64/Linux (Suse 9.1) and I get the
following error while running the configure script.
...
checking for dummy main to link with Fortran libraries... none
checking for Fortran name-mangling
Hello,
I'm a newbie on this list.
I have a R code but its execution take a very long time.
Is it possible to compile it (in C for example) to decrease the execution
time ?
--
Alexandre DEPIRE
INRETS / GARIG
__
Thank you, John! it is exactly what I need...looking forward to apply it
Anne
what would I become without this list?
- Original Message -
From: John Fox [EMAIL PROTECTED]
To: 'Anne' [EMAIL PROTECTED]
Cc: 'R list' r-help@stat.math.ethz.ch
Sent: Friday, January 07, 2005 3:56 PM
Subject:
Are you referring to this statement from the R FAQs for Mac OS X?
In same cases you can still build packages without all the tools
installed, but surely not for all the packages containing C/C++ or
Fortran source code.
It is saying that if you do *not* have all the tools installed on
your Mac,
On Fri, 7 Jan 2005 [EMAIL PROTECTED] wrote:
On 07-Jan-05 NDIKUMAGENGE Alice wrote:
Hello,
I've tried stl decomposition but I made a mistake
I want to make a calibration on a sample, in french we called it
Redressement d'un échantillon
Thank u
Are you referring to the sort of thing decsribed, for
Fred,
If you want to produce log normal values you can do it by using rlnorm,
and you have to provide the mean and variance of the process in log
scale, wich means after log transform. Or you can produce them with
rnorm and exponentiate.
Check:
set.seed(1)
rlnorm(100, 0, 1)-vec
set.seed(1)
Bonne année Al Gamous
Tu vas bien ?
Tes nouvelles ?
A bientôt
Said Hourrane
[EMAIL PROTECTED]
[[alternative HTML version deleted]]
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the
Hi Gudrun,
try the following:
y - rbinom(100, 1, 0.5)
x - rnorm(100)
##
glm(y~x, family=binomial)
glm(y~x-1, family=binomial)
I hope it helps.
Best,
Dimitris
Dimitris Rizopoulos
Ph.D. Student
Biostatistical Centre
School of Public Health
Catholic University of Leuven
Address:
Gudrun Jonasdottir [EMAIL PROTECTED] writes:
Dear R-help list members,
I am currently trying to fit a generalized linear model using a binomial
with the canonical link. The usual solution is to use the R function glm()
in the package stats. However, I run into problem when I want to fit a
Dear Christoph,
as.vector(as.matrix(DF))
[1] A B A B C A C A B
does the trick.
Regards,
John
John Fox
Department of Sociology
McMaster University
Hamilton, Ontario
Canada L8S 4M4
905-525-9140x23604
http://socserv.mcmaster.ca/jfox
[EMAIL PROTECTED] wrote:
Dear list,
I do have a problem with nls. I use the following data:
test
time conc dose
0.50 5.401
0.75 11.101
1.00 8.401
1.25 13.801
1.50 15.501
1.75 18.001
2.00 17.001
2.50 13.901
3.00 11.201
3.50
As in any modelling situation in R or S, to suppress the
intercept you simply put a ``-1'' in the formula. E.g.:
fit - glm(y~x-1,family=binomial)
cheers,
Rolf Turner
[EMAIL PROTECTED]
On Fri, 2005-01-07 at 15:47 +0100, Christoph Scherber wrote:
Dear all,
I have a data frame that looks like this:
c1 c2 c3
ABC
BCA
AAB
and so on;
Id like to produce one single vector consisting of the columns c1,c2,
c3, such that
Christoph Scherber wrote:
Dear all,
I have a data frame that looks like this:
c1 c2 c3
ABC
BCA
AAB
and so on;
I´d like to produce one single vector consisting of the columns c1,c2,
c3, such that
vector=(A,B,A,B,C,A,C,A,B)
I guess it´s easy to do but I don´t know
if your dataframe is called foo,
as.vector(foo)
Quoting Christoph Scherber [EMAIL PROTECTED]:
Dear all,
I have a data frame that looks like this:
c1 c2 c3
ABC
BCA
AAB
and so on;
I´d like to produce one single vector consisting of the columns
Depire Alexandre wrote:
Hello,
I'm a newbie on this list.
I have a R code but its execution take a very long time.
Is it possible to compile it (in C for example) to decrease the execution
time ?
a) R is not C.
b) No, we don't have an R compiler (except - in development - a byte
compiler written
How about
as.vector(x)
where x is the data?
BTW a matrix in R is stored as a vector anyways (IIRC).
--
[EMAIL PROTECTED]
You will feel hungry again in another hour.
It is rumored that on Fri, 07 Jan 2005 15:47:04 +0100
Christoph Scherber [EMAIL PROTECTED] wrote:
Dear all,
I
On Fri, 7 Jan 2005, Gudrun Jonasdottir wrote:
I am currently trying to fit a generalized linear model using a binomial
with the canonical link. The usual solution is to use the R function glm()
in the package stats. However, I run into problem when I want to fit a
glm without an intercept. It is
Coercion to matrix then to vector should work:
dat
V1 V2 V3
1 A B C
2 B C A
3 A A B
as.vector(as.matrix(dat))
[1] A B A B C A C A B
Andy
From: Christoph Scherber
Dear all,
I have a data frame that looks like this:
c1 c2 c3
ABC
BCA
AAB
and
R is basically an interpreted language. To my knowledge, the
standard approach to improving speed starts by finding which steps take
the most time. This can be done using proc.time and / or
system.time (preceded by gc to clean things up so the timing is more
stable).
Once you've
Hi,
To write a constructor for an S4 object, you make an initialize method
which will be called by new. But how would I make a destructor method to
be called when the S4 object is garbage collected? I'm looking at
reg.finalizer, but I'm not sure how to make that work for an S4 object.
I want to
i'm coding in R(first time) for a paper my colleague is publishing.
i plotted a histogram for 6000 values. Taking the mean and sd of the
midpoints i did a dnorm and got the densities.
pl-dnorm(trimmedvals,mean=midsmean,sd=midsSD)
(now in a loop of 5 times)
i plotted these experimental
Hi, Doug:
How would you diagnose something like this? For example, might
the following (from ?nlsModel) help:
DNase1 - DNase[ DNase$Run == 1, ]
mod -
nlsModel(density ~ SSlogis( log(conc), Asym, xmid, scal ),
DNase1, start=list( Asym = 3, xmid = 0, scal = 1 ))
It **sounds ** like you are trying to fit a nonparametric density to 6000
values... If so, please stop what you are doing and see ?density. You could
also search on fit density or something similar on the R site search, as
there are other R functions in R packages that do density fitting (ash is
For figuring out where in the code the bottleneck is, a better tool is
probably the profiler. See:
http://cran.r-project.org/doc/manuals/R-exts.html#Profiling%20R%20code
HTH,
Andy
From: Spencer Graves
R is basically an interpreted language. To my knowledge, the
standard approach
There was a real compiler which was under development as a MS thesis
at Rice U last year, but I'm not sure if it was finished or ever will
be released. I actually saw it in action on a small example...
best,
-tony
On Fri, 7 Jan 2005 16:12:56 +0100, Depire Alexandre [EMAIL PROTECTED] wrote:
From: A.J. Rossini
There was a real compiler which was under development as a MS thesis
at Rice U last year, but I'm not sure if it was finished or ever will
be released. I actually saw it in action on a small example...
best,
-tony
Yes: http://hipersoft.cs.rice.edu/rcc/
(I believe
Doesn't look like nonparametric fit to me, since nls() is used to fit to a
gaussian density, so the result is a gaussian density (with estimated
parameter).
What I do not understand is why people would do this. This is not the first
time I've seen people doing this, on both R-help and S-news (if
Is it correct (by its lack of mention in the R-Language Definition
Manual) that it is impossible to create a user-defined unary operator?
Ex: (This doesn't work, but it's an example of what I'm looking for)
%PLUSONE% - function(x) x + 1
%PLUSONE% 2
[1] 3
And if the above is impossible, am I
Hi,
This might be a general question: I am comparing two
groups using Wilcoxon rank sum test. However, the size
of the two groups differ a lot, e.g., one group has 20
and the other has 1. Is the test still appropriate
given this huge disparity in size? If yes, what is the
alternative?
Robert:
VR's S-PROGRAMMING is an indispensable reference for sophisticated R
programming issues like those you bring up. Also the John Chambers Green
book (Programming with Data ...)might be useful .
I would await definitive confirmation from the experts, but AFAIK you're
correct -- you can only
On Fri, Jan 07, 2005 at 05:14:29PM +0100, Peter Dalgaard wrote:
Gudrun Jonasdottir [EMAIL PROTECTED] writes:
Dear R-help list members,
I am currently trying to fit a generalized linear model using a binomial
with the canonical link. The usual solution is to use the R function glm()
Dear ALL,
In order to install the Rice R to C compiler (RCC) you need to patch the R
source code. However, the patch command at DOS prompt returns an error: patch
is not recognized as internal or external command. How do you patch in DOS (or
Windows)?
Regards,
Samuel.
On Fri, 2005-01-07 at 16:00 -0800, Sameul M Mwalili wrote:
Dear ALL,
In order to install the Rice R to C compiler (RCC) you need to patch
the R source code. However, the patch command at DOS prompt returns an
error: patch is not recognized as internal or external command. How
do you patch in
Uwe Ligges wrote on 07 Jan 2005 09:16:09 MET:
Patrick Drechsler wrote:
I was wondering if it's possible to have fonts in plots to be
autoscaled to the same font size used by LaTeX in a
surrounding Sweave document.
See ?strwidth which might help for the required calculations.
Thanks for
Hi Friedrich,
Friedrich Leisch wrote on 07 Jan 2005 09:49:04 MET:
thanks for taking the time!
On Thu, 06 Jan 2005 23:56:31 +0100,
Patrick Drechsler (PD) wrote:
I was wondering if it's possible to have fonts in plots to be
autoscaled to the same font size used by LaTeX in a
surrounding
Hi,
I just compiled R on solaris.
Everything seems to run fine.
Except, the up and down arrows don't take me
through the history. See:
===
~/R-2.0.1/bin: R
R : Copyright 2004, The R Foundation for Statistical Computing
Version 2.0.1
On Fri, Jan 07, 2005 at 11:56:46PM -0500, a j wrote:
I just compiled R on solaris.
Everything seems to run fine.
Except, the up and down arrows don't take me
through the history. See:
[...]
How can I get these arrows to take me through history?
It's a FAQ -- you need readline
On Fri, 7 Jan 2005, Marc Schwartz wrote:
On Fri, 2005-01-07 at 16:00 -0800, Sameul M Mwalili wrote:
Dear ALL,
In order to install the Rice R to C compiler (RCC) you need to patch
the R source code. However, the patch command at DOS prompt returns an
error: patch is not recognized as internal or
On Fri, 7 Jan 2005, Dirk Eddelbuettel wrote:
On Fri, Jan 07, 2005 at 11:56:46PM -0500, a j wrote:
I just compiled R on solaris.
Everything seems to run fine.
Except, the up and down arrows don't take me
through the history. See:
[...]
How can I get these arrows to take me through history?
It's a
82 matches
Mail list logo