This is the consequence of the use of partial likelihood in the Cox model.
You should read the literature on this point (for example, have you read
Cox, 1972 and all its discussion, or Anderson, Borgan, Gill & Keiding?).
It is not an R question. You need to make more assumptions, such as a
smoot
Hi,
hints for your r-related day ahead predictions you find in the second part
of Louis Torgo's very usefuel: DataMining with R
http://www.liacc.up.pt/~ltorgo/ DataMiningWithR/PDF/DataMiningWithR.pdf
And for your PL/SQL intention:
http://www.omegahat.org/RSPostgres/
christian
Am Donnersta
The Bioconductor project posts a short tutorial "A guide to using S4
Objects" under "Developer Page" frame. I've found it useful.
Note that R-s S4-classes approach to OOP is very different from the one
of C++ or Java. Yet you will find member vars, they are called slots.
> -Original Message-
Hi,
I'm looking for resources to read about the object-oriented features of R.
I have looked through the "Manuals" page on r-project.org. The most
useful of the documents seemed to be the "draft of the R language
definition". However it had only about 6 pages on the topic.
I have also used Go
Robert,
Thank you for your reply. I thought RSXML was an R (CRAN) package? I
realize your package is part of bioconductor so I'll try the
bioconductor mailing list as well.
Also and more importantly I took your suggestion and stepped through the
calls. It seems the failure in pm.getabst() oc
Trenkler, Dietrich said:
>
> I found the following strange behavior using qnorm() and pnorm():
>
> > x<-8.21;x-qnorm(pnorm(x))
> [1] 0.0004638484
> > x<-8.28;x-qnorm(pnorm(x))
> [1] 0.07046385
> > x<-8.29;x-qnorm(pnorm(x))
> [1] 0.08046385
> > x<-8.30;x-qnorm(pnorm(x))
> [1] -Inf
>
qnorm(1-.Machi
> I have many variables to test using cox model (coxph), and I am only
interested in those variables with p value less than 0.01. Is there a
quick way to do this automatically instead of looking at the output of
each variable?
> Chris
I guess you need covariate selection.
for a lengthy discussion
Hello,
coxph does not use any information that are in the dataset between event
times (or "death times") , since computation only occurs at event times.
For instance, removing observations when there is no event at that time in
the whole dataset does not change the results:
> set.seed(1)
> data
Hi all,
I have many variables to test using cox model (coxph), and I am only interested in
those variables with p value less than 0.01. Is there a quick way to do this
automatically instead of looking at the output of each variable?
Plus, is there a method in R that I could adjust the multiple t
You will almost surely do better to ask about Bioconductor packages on
the Bioconductor mailing list. Next, it is helpful to know what
versions of things you are using.
As for your problem, did you look to see what kind of object absts is?
There seems to be no default method for xmlRoot, and it is
On Thu, 12 Aug 2004, Michael Jerosch-Herold wrote:
> I am using the latest version of R on a Windows machine and get the
> following error when I try to initialize a correlation structure with
> the function corAR1 in NLME. This example is taken from the book of
> Pinheiro and Bates, so it should
I am using the latest version of R on a Windows machine and get the
following error when I try to initialize a correlation structure with
the function corAR1 in NLME. This example is taken from the book of
Pinheiro and Bates, so it should work. What is going wrong?
> library(nlme)
> data(Orthodont
R Users:
After installing Bioconductor, RSXML and all the relevant Win32 DLLs (libxml2, zlib,
iconv), I receive the following error message when using pm.getabst()
Error in xmlRoot(absts) : no applicable method for "xmlRoot"
I receive this when using the example from help(pm.getabst).
Downlo
Thanks a lot for the assistance. It was an installation mistake - apparently
we did not have BLAS libraries installed. The compiler did not seem to have
been a problem in this case, althought it is an older version (gcc 3.3.1).
Mario.
>-Original Message-
>From: Prof Brian Ripley [mailto:[
Hi r-people :)
I'm sorry to disturb but I must admit that I know amazingly little about R and
similar statistics-packages/languages and I'm kind of lost on where to start.
I'm currently working on a datacollection framework for postgresql (The db
doesn't really matter except that I hope to use P
On Thu, 12 Aug 2004, Richard Urbano wrote:
> I have this snippet of code from an example in Dr. Harrel's book "Regression
> Modeling Strategies" p 501
That's in a section called `S-PLUS Examples'.
^^
> n<-2000
> .Random.seed <-c(49,39,17,36,23,0,43,51,6,54,50,1)
>
I have this snippet of code from an example in Dr. Harrel's book "Regression
Modeling Strategies" p 501
n<-2000
.Random.seed <-c(49,39,17,36,23,0,43,51,6,54,50,1)
age <-50 + 12 * rnorm(n)
age
I get the error message: Error in rnorm(n) : .Random.seed[1] is NOT a valid
RNG kind (code)
On Thu, 12 Aug 2004, Seth Falcon wrote:
> The thing that's very different from, say, Java is that everything is an
> object in R --- there isn't a notion of a *reference* to an object,
> which is why in the above I had to say "head <- insertNode(...)" where
> as in Java you could pass in a referen
On Thu, 12 Aug 2004, Jason Liao wrote:
> Dear Thomas,
> Thank you very much again for taking time to answer my questions. I am
> sorry that my knoweldge of R is limited as I have only learned what is
> necessary to do my work. In the KD tree, we have this recursive data
> structure in that each kn
Dear useRs,
my last announcement is an update of the ineq package
for measuring inequality, concentration and poverty.
The current version is now 0.2-4.
Thanks to suggestions from Rein Halbersma the Pen()
function for plotting Pen's parade was improved and now
allows for much more flexibility. Se
Dear useRs,
the strucchange package for testing for structural change
has been updated: the current version is 1.2-4.
The most significant additions were two functions gefp()
and efpFunctional().
gefp() implements a class of generalized M-fluctuation
tests for testing for parameter instability or
Dear useRs,
yet another "new" package: zoo 0.2-0.
zoo provides a simple S3 class and methods for totally
ordered indexed observations such as irregular time
series. Although there are other packages for irregular
time series available on CRAN (Giles Heywood's its
package and irts() in Adrian Tra
Dear useRs,
here is the announcement for the next "new" package:
sandwich 0.1-3.
sandwich provides heteroskedasticity (and autocorrelation)
consistent covariance matrix estimators (also called HC
and HAC estimators).
The former are implemented in the function vcovHC() (which
was available in str
Dear useRs,
I used the summer months to work on all of my packages,
and so this is the first of a sequence of announcements
of "new" or updated packages. The "new" packages are new
in the sense that previous versions had been on CRAN for
some months but hadn't been announced to the R community
vi
Jason Liao yahoo.com> writes:
> In the KD tree, we have this
>[...]
> recursive data structure? If yes, can you give a sample program?
>
For an example, see the R loess.smooth function which uses k-d trees.
Try ?loess.smooth for info and just type
loess.smooth
like that exactly to see s
Hi Jason,
On Thu, Aug 12, 2004 at 10:20:14AM -0700, Jason Liao wrote:
> Does R's list support this recursive data structure? If yes, can you
> give a sample program?
Not sure if this is what you are looking for, but here's a quick linked
list example using R's lists.
# -8<---
Hi,
I am using the rgl package for 3D display. Unfortunately, I am not able
to get the snapshot command running.
I tried the following:
> example(rgl.surface)
rgl.sr> data(volcano)
rgl.sr> y <- 2 * volcano
rgl.sr> x <- 10 * (1:nrow(y))
rgl.sr> z <- 10 * (1:ncol(y))
rgl.sr> ylim <- range(y)
rgl.sr
Dear Thomas,
Thank you very much again for taking time to answer my questions. I am
sorry that my knoweldge of R is limited as I have only learned what is
necessary to do my work. In the KD tree, we have this recursive data
structure in that each knod has two children knods and this process
continu
On Thu, 12 Aug 2004, Jason Liao wrote:
> Good morning! I recently implemented a KD tree in JAVA for faster
> kernel density estimation (part of the code follows). It went well. To
> hook it with R, however, has proved more difficult. My question is: is
> it possible to implement the algorithm in R
For an overview of the OOP R package, see
http://cran.r-project.org/doc/Rnews/Rnews_2001-3.pdf
+ seth
__
[EMAIL PROTECTED] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide
> From: Barry Rowlingson
>
> Thomas Lumley wrote:
> > On Thu, 12 Aug 2004, Rau, Roland wrote:
> >
> >>That is why would like to ask the experts on this list if
> anyone of you has
> >>encountered a similar experience and what you could advise
> to persuade
> >>people quickly that it is worth le
On Tue, Aug 10, 2004 at 04:53:49PM +0200, Klaus Juenemann wrote:
> If you don't organize your code into packages but source individual R
> files your approach to source the code at the beginning of a test file
> looks the right thing to do.
Appears to be working pretty well for me too ;-)
> We ma
Rau, Roland demogr.mpg.de> writes:
> Yes, I do know the R-Commander. But I did not want to give them a
> GUI but rather expose them to the command line after I demonstrated that the
> steep learning curve in the beginning is worth the effort for the final
> results.
Note that Rcmdr display
[Reverted back to R-help, after private exchange]
> "MM" == Martin Maechler <[EMAIL PROTECTED]>
> on Thu, 12 Aug 2004 17:12:01 +0200 writes:
> "javier" == javier garcia <- CEBAS <[EMAIL PROTECTED]>>
> on Thu, 12 Aug 2004 16:28:27 +0200 writes:
javier> Martin; Yes I kn
>From Spencer Graves:
>However, for an equality constraint, I've had good luck by with an objective function
>that adds something like the
>following to my objective function: constraintViolationPenalty*(A%*%theta-c)^2, where
>"constraintViolationPenalty" is
>passed via "..." in a call to optim.
Jason Liao yahoo.com> writes:
:
: Good morning! I recently implemented a KD tree in JAVA for faster
: kernel density estimation (part of the code follows). It went well. To
: hook it with R, however, has proved more difficult. My question is: is
: it possible to implement the algorithm in R? My
Good morning! I recently implemented a KD tree in JAVA for faster
kernel density estimation (part of the code follows). It went well. To
hook it with R, however, has proved more difficult. My question is: is
it possible to implement the algorithm in R? My impression seems to
indicate no as the code
Thomas Lumley wrote:
On Thu, 12 Aug 2004, Rau, Roland wrote:
That is why would like to ask the experts on this list if anyone of you has
encountered a similar experience and what you could advise to persuade
people quickly that it is worth learning a new software?
The usual way of teaching R seem
On Thu, 12 Aug 2004, Rau, Roland wrote:
>
> That is why would like to ask the experts on this list if anyone of you has
> encountered a similar experience and what you could advise to persuade
> people quickly that it is worth learning a new software?
One problem is that it may not be true. Unles
Consider using the HyperbolicDist package. With the package you can both fit the
hyperbolic distribution to your data and generate random numbers from the
distribution. Hyperbolic distribution/s provide/s good fit to financial returns that
commonly exhibit high peaks and heavy tails.
Hannu Kahr
The message for aov1 was "Estimated effects be unbalanced". The
effects are not unbalanced. The design is 'orthogonal'.
The problem is that there are not enough degrees of freedom to estimate
all those error terms. If you change the model to:
aov1 <-
aov(RT~fact1*fact2*fact3+Error(sub/
¡Hola Javier!
since I am the maintainer of the cluster
*package* (not "library"), I'm interested to find out more about
this problem. I assume, you now use R 1.9.1.
Can you give us an example we can reproduce?
Give the exact R commands you use and
maybe attach the save()d data file (*.rda) in
On Thu, 12 Aug 2004, Martin Maechler wrote:
> > "Vito" == Vito Ricci <[EMAIL PROTECTED]>
> > on Thu, 12 Aug 2004 10:59:23 +0200 (CEST) writes:
>
> Vito> Hi, Also the Cauchy's distribution could be good:
>
> Vito> rcauchy(n, location = 0, scale = 1)
>
> "also" is an exaggerat
On Thu, 12 Aug 2004, Doran, Harold wrote:
> lme fits models using restricted maximum likelihood by default. So, I
> believe this is why you have a different DF. If you include method="ML"
> in the modeling function the DF should be similar to aov.
It is REML and not ML that generalizes the class
> "Vito" == Vito Ricci <[EMAIL PROTECTED]>
> on Thu, 12 Aug 2004 10:59:23 +0200 (CEST) writes:
Vito> Hi, Also the Cauchy's distribution could be good:
Vito> rcauchy(n, location = 0, scale = 1)
"also" is an exaggeration, after you already told him to use the
t-distribution fam
Dear Gijs:
lme fits models using restricted maximum likelihood by default. So, I believe this is
why you have a different DF. If you include method="ML" in the modeling function the
DF should be similar to aov.
I think your lme code is incorrect given my understanding of your problem. You can
Hi,
I'm using the cluster library to examine multivariate data.
The data come from a connection to a postgres database, and I did a short R
script to do the analisys. With the cluster version included in R1.8.0, daisy
worked well for my data, but now, when I call daisy, I obtain the following
me
Hi,
I have encountered big difficulties trying to persuade my undergraduate
students, with very "slight" background either in statistics or computing to
use R instead of SPSS.
I tried to start with a sort of very, very simple sample session, just for
showing that R is not as complicated as they
Hi,
> -Original Message-
> From: Vito Ricci [SMTP:[EMAIL PROTECTED]
> do you know there are several GUI for R? See:
[...]
> R-Commander is quite like GUI of commercial softwares.
>
>
Yes, I do know the R-Commander. But I did not want to give them a
GUI but rather expose t
Hi,
do you know there are several GUI for R? See:
http://www.sciviews.org/_rgui/
and in particular:
http://socserv.mcmaster.ca/jfox/Misc/Rcmdr/
R-Commander is quite like GUI of commercial softwares.
Give a look: they can help your pupils which are able
to use SPSS.
Although I prefer command li
Dear all,
in the coming Winter Semester, I will be a teaching assistant for a course
in Survival Analysis. My job will be to do the lab sessions. The software
used for these lab sessions will be R. Most of the students have a
background in social sciences and the only stats package they used so fa
Hi,
Also the Cauchy's distribution could be good:
rcauchy(n, location = 0, scale = 1)
Best
Vito
I would be very grateful for any help from members of
this list for what
might be a simple problem...
We are trying to simulate the behaviour of a clinical
measurement in a
series of computer expe
Hi,
the Student's t distribution could be considered:
it's symmetrical, but with a low number of degree of
freedom is different from Normal distribution I think
in the way you said:"has a much higher peak at the
mean and the distribution has much longer
tails. " Try to use:
rt(n, df) where n=nu
Hi David,
you could try a Student's t distribution with appropriate degrees of
freedom and extra scale paremter, i.e.,
?rt
rgt <- function(n, mu=0, sigma=1, df=stop("no df arg")) mu+sigma*rt(n,
df=df)
I hope this helps.
Best,
Dimitris
Dimitris Rizopoulos
Doctoral Student
Biostatistical Ce
I would be very grateful for any help from members of this list for what
might be a simple problem...
We are trying to simulate the behaviour of a clinical measurement in a
series of computer experiments. This is simple enough to do in R if we
assume the measurements to be Gaussian, but their empi
I will follow the suggestion of John Maindonald and present the problem
by example with some data.
I also follow the advice to use mean scores, somewhat reluctantly
though. I know it is common practice in psychology, but wouldn’t it be
more elegant if one could use all the data points in an ana
56 matches
Mail list logo
