In fact, there some common IRT models that ltm cannot currently
handle, e.g., the three-parameter logistic model or the graded
response model; however, I do plan to incorporate these models in the
near future.
Best,
Dimitris
- Original Message -
From: Doran, Harold [EMAIL
Hi
It is not so clear to me what your intention is. Could you
provide a reproducible example to show what you want to do.
Regards,
Christoph Buser
--
Christoph Buser [EMAIL PROTECTED]
Seminar fuer Statistik, LEO C13
ETH (Federal
On 26 Nov 2005 at 15:40, Wei Qiu wrote:
Date sent: Sat, 26 Nov 2005 15:40:52 -0500 (EST)
From: Wei Qiu [EMAIL PROTECTED]
To: Gabor Grothendieck [EMAIL PROTECTED]
Copies to: r-help r-help@stat.math.ethz.ch
Subject:
Hallo
I encountered a behaviour which puzzles me (but
finally I did get what I wanted).
I used structable and strucplot but I wanted to change
names of variables in structable object. I tried to subset
it, use names but to no avail. So I tried str and
expected to get a structure of an object
___
Hi,
I was just wondering if there was any available R code that could handle
general constrained optimisation problems. At the moment I'm using
nlminb and optim, both of which allow box constraints on the
In the R Document, the usage of the acf() is as follow:
acf(x, lag.max = NULL,
type = c(correlation, covariance, partial),
plot = TRUE, na.action = na.fail, demean = TRUE, ...)
But now I want to get the result picture like:
plot(x,type=l)
or
plot(x,type=p)
How can I do this with acf
Hi, I wonder if there is a package aimed at comparing two scoring systems.
Such as, to compare a student's performance (scores or ranks) in two
different testing systems to find out if they are consistent?
Sorry if this question is too naive. It seems easy but just wonder if there
are handy
Hello,
I have a classification tree. I want to obtain a ROC curve for this
test. What is the easiest way to obtain one?
-Anjali
did you try the ROCR package ?
regards,
Hans Vermeiren
__
R-help@stat.math.ethz.ch
You've posed an excellent question with simple and elegant,
reproducible example. I've seen no replies, so I will attempt a partial
response. RSiteSearch(lexical scoping) produced some potentially
useful comments (e.g.,
http://finzi.psych.upenn.edu/R/Rhelp02a/archive/37769.html),
I am trying to use KalmanSmooth to smooth a time series
fitted by arima (and with missing values), but the $smooth component
of the output baffles me. Look at the following example:
testts - arima.sim(list(ar=0.9),n=100)
testts[6:14] - NA
testmod - arima(testts, c(1,0,0))
testsmooth -
Petr Pikal wrote:
Hallo
I encountered a behaviour which puzzles me (but
finally I did get what I wanted).
I used structable and strucplot but I wanted to change
names of variables in structable object. I tried to subset
it, use names but to no avail. So I tried str and
expected to
We have uploaded to CRAN the first version of glmpath,
which fits the L1 regularization path for generalized linear models.
The lars package fits the entire piecewise-linear L1 regularization
path for
the lasso. The coefficient paths for L1 regularized glms, however,
are not piecewise
Petr == Petr Pikal [EMAIL PROTECTED]
on Mon, 28 Nov 2005 08:38:07 +0100 writes:
Petr Hallo I encountered a behaviour which puzzles me (but
Petr finally I did get what I wanted).
Petr I used structable and strucplot but I wanted to change
Petr names of variables in
HI LIST
i am a new R user,i am trying to make a model,which will give me
output in probability,which will take predictors series as input and my
predictand as output.What is the package and what is the function for
probability model.What are the possible methods for fitting such
I encountered a behaviour which puzzles me (but
finally I did get what I wanted).
I used structable and strucplot but I wanted to change
names of variables in structable object.
I tried to subset
it, use names but to no avail. So I tried str and
expected to get a structure
On Mon, 28 Nov 2005, [gb2312] ¹ãÐÇ wrote:
In the R Document, the usage of the acf() is as follow:
acf(x, lag.max = NULL,
type = c(correlation, covariance, partial),
plot = TRUE, na.action = na.fail, demean = TRUE, ...)
But now I want to get the result picture like:
plot(x,type=l)
or
hi all
i have a few questions about formatting plots:
1. i would like to add a symbol such as chi squared with 3 degrees of freedom
onto a plot.expression(chi^2 == jnfdjb), can be used in conjuction with
legend to solve this but how does one include an under score for the degrees
of
On Thu, 24 Nov 2005, Benjamin Lloyd-Hughes wrote:
Ok I warned you that I'd been drinking! What I really meant was
something to go from:
[,1] [,2]
[1,]12
[2,]43
to
[,1] [,2]
[1,]41
[2,]32
to
[,1] [,2]
[1,]34
[2,]21
The error is in anova.gls(): traceback() would have told you that was
involved. It ends
do.call(anova.lme, as.list(match.call()[-1]))
and that call needs to be evaluated in the parent, not in the body of
anova.lme. Several similar errors (e.g. in the update methods) in package
nlme have
[EMAIL PROTECTED] wrote:
hi all
i have a few questions about formatting plots:
1. i would like to add a symbol such as chi squared with 3 degrees of freedom
onto a plot.expression(chi^2 == jnfdjb), can be used in conjuction with
legend to solve this but how does one include an under
Oops,I got it!
plot(acf(x,plot=false),type=l,col=red)
will be OK!
Thank you very much!
=== 2005-11-28 18:09:03 您在来信中写道:===
On Mon, 28 Nov 2005, [gb2312] 广星 wrote:
In the R Document, the usage of the acf() is as follow:
acf(x, lag.max = NULL,
type = c(correlation,
# Hello R Users,
#
# I would like to fit a glm model with quasi family and
# logistical link function, but this does not seam to work
# with binary data.
#
# Please don't suggest to use the quasibinomial family. This
# works out, but when applied to the true data, the
# variance function does not
Hi all,
How can I stop my xemacs from lauching R whenever it starts? I want to use
the usual M-x R instead.
This is something I have to edit in the init file.
Thanks
Mahdi
--
---
Mahdi Osman (PhD)
E-mail: [EMAIL PROTECTED]
Hi all,
I'm trying to make a plot with the function xYplot from package Hmisc in
R. I would like to have minor tick-marks on the axis. This should be a
common simple feature to have but I don't seem to find any discussion on
the topic.
Following is one of the things I tried and the error
Dear R users:
I am looking for information on how to compute the error in an estimation of
the expentancy of life using survival analysis methods. I am interesting either
in the theoretical calculations or in the way to carry out the analysis using
R. I know that the mean life can be computed
Björn Stollenwerk wrote:
# Hello R Users,
#
# I would like to fit a glm model with quasi family and
# logistical link function, but this does not seam to work
# with binary data.
#
# Please don't suggest to use the quasibinomial family. This
# works out, but when applied to the true
Hi list,
Is there a way to process R commands in the background other then using
R in batch mode? I'm looking for the equivalent of the operator on the
*nix commandline.
Cheers,
Koen
__
R-help@stat.math.ethz.ch mailing list
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Dear list members,
my problem is to analyze multiple variables by using a simple loop.
Without a loop, no problem:
fit1 - fit.mult.impute(variable_from_MIC_datset ~ group, fitter=ols,
xtrans=imp.dmat)
Without a multiple imputation data set, that works:
vars - c(
lverb.ona, l2, lalles.ona, vl,
Hey Koen,
Is there a way to process R commands in the background other then using
R in batch mode? I'm looking for the equivalent of the operator on the
*nix commandline.
Well, that's not R-specific, but what I do is to use screen, which is
a handy little program that emulates multiple
Hello,
I read a book about statistics in psychology. The authors use SPSS. They
talk about post hoc tests after ANOVA finds significant effects:
- Gabriel's procedure (for equal or slightly different sample sizes)
- Hochberg's GT2 (for different sample sizes)
- Games-Howell procedure
Mahdi Osman m_osm at gmx.net writes:
How can I stop my xemacs from lauching R whenever it starts? I want to use
the usual M-x R instead.
This is something I have to edit in the init file.
Remove
(start-R)
at the end of the init file (assuming you use the John-Fox Version).
Dieter
Hello,
I try to define a global variable.
My example:
R a - old
R test - function () { a - new }
R test()
R a # shoud be new
This doesn't work. I would like to modify the variable a in a
procedure. How can I do that.
Thank you for helping.
Sven Knüppel (Germany-Berlin)
I am sososo sorry for my inattention to my EMail's format!
I have change that.
Thank you very much again!
=== 2005-11-28 21:19:16 Write:===
$A9cPG(B == $A9cPG(B [EMAIL PROTECTED]
on Mon, 28 Nov 2005 19:16:31 +0800 writes:
$A9cPG(B Oops,I got it!
The problem is that the a is within the function
You can easily solve this by
test - function () { a - new; return(a) }
a=test()
Best regards,
Kristel
(or test - function () { return(a - new)})
[EMAIL PROTECTED] wrote:
Hello,
I try to define a global variable.
My example:
R a - old
try
a - old
test - function () { assign(a, new, envir = .GlobalEnv) }
test()
a
I hope it helps.
Best,
Dimitris
Dimitris Rizopoulos
Ph.D. Student
Biostatistical Centre
School of Public Health
Catholic University of Leuven
Address: Kapucijnenvoer 35, Leuven, Belgium
Tel: +32/(0)16/336899
[EMAIL PROTECTED] wrote:
R a - old
R test - function () { a - new }
R test()
R a # shoud be new
This doesn't work. I would like to modify the variable a in a
procedure. How can I do that.
You may like to modify the variable, but who else wants you to?
Functions should have zero side
Try,
# work directly with data from the input files
directory = system.file(Test, package = caMassClass)
X = msc.rawMS.read.csv(directory, IMAC_normal_.*csv)
Peaks = msc.peaks.find(X) # Find Peaks
cat(nrow(Peaks), peaks were found in, Peaks[nrow(Peaks),2], files.\n)
stopifnot(
In your current definitions a can not change value to
new unless you type a-test(). If you want the
results of the test to be global then you add something like this
test -function()a-new
This will always replace the existing value of a once
you type test()
regards
Anthony- Original
[EMAIL PROTECTED] wrote:
Hello,
I try to define a global variable.
You should not do that unless you really know why you want it this way.
You probably want to read the R Language Definition manual.
Anyway, read ?assign if you want to proceed doing dangerous things.
Uwe Ligges
My
I have to estimate the following model for several
group of observations :
y(1-y) = p[1]*(x^2-y) + p[2]*y*(x-1) + p[3]*(x-y)
with constraints :
p[1]+p[3] = 1
p[1]+p[2]+p[3]+1 = 0
p[3] = 0
I use the following code :
func - sum((y(1-y) - p[1]*(x^2-y) + p[2]*y*(x-1) +
p[3]*(x-y))^2)
estim -
See:
http://tolstoy.newcastle.edu.au/~rking/R/help/05/11/15737.html
and the responses.
On 11/28/05, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote:
Hello,
I try to define a global variable.
My example:
R a - old
R test - function () { a - new }
R test()
R a # shoud be new
This doesn't
See, my old post at
http://finzi.psych.upenn.edu/R/Rhelp02a/archive/61879.html
to see a list of ROC related packages and functions. One of them should
work well for your application. All of them take data in the form:
- x - real number value returned by the classifier
- y - true labels /
Hello,
Is there any function to display a waitbar window (using tclTk ?)
Thanks for any help !
D. Ecotière
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
Florent Bresson [EMAIL PROTECTED] writes:
I have to estimate the following model for several
group of observations :
y(1-y) = p[1]*(x^2-y) + p[2]*y*(x-1) + p[3]*(x-y)
with constraints :
p[1]+p[3] = 1
p[1]+p[2]+p[3]+1 = 0
p[3] = 0
I use the following code :
func - sum((y(1-y) -
On Mon, 28 Nov 2005, Florent Bresson wrote:
I have to estimate the following model for several
group of observations :
y(1-y) = p[1]*(x^2-y) + p[2]*y*(x-1) + p[3]*(x-y)
with constraints :
p[1]+p[3] = 1
p[1]+p[2]+p[3]+1 = 0
p[3] = 0
I use the following code :
func - sum((y(1-y) -
If I understand this correctly the variables over which
you are optimizing are p[1], p[2] and p[3] whereas x and y
are fixed and known during the optimization. In that case its
a linear programming problem and you could use the lpSolve
library which would allow the explicit specification of the
Hi,
I have three questions concerning GLMMs.
First, I ' m looking for a measure for the significance of the random variable
in a glmm.
I'm fitting a glmm (lmer) to telemetry-locations of 12 wildcat-individuals
against random locations (binomial response). The individual is the random
variable.
Dear Prof. Ripley:
Thanks very much. I tried several superficially similar things but
not either of the solutions you suggest.
Best Wishes,
spencer graves
Prof Brian Ripley wrote:
The error is in anova.gls(): traceback() would have told you that was
involved.
Hello to everyone!...
I would like to ask you if there is a way to extract the known
Durbin-Watson critical values (D_L and D_U - lower and upper limits)
within R, as we do in the DW statistic tables at the end of
Econometrics Textbooks, because packages car and lmtest seem to
provide only the
Dear R people,
I am currently experimenting with graph plotting using libraries
Rgraphviz, graph, etc. as needed by GeneTS (bioconductor project).
The plots I get use huge fonts to label the nodes and the edges
and that often makes the plot unreadable (overlapping edge labels etc).
The
On Mon, 28 Nov 2005, Hong Ooi wrote:
Hi,
I was just wondering if there was any available R code that could handle
general constrained optimisation problems. At the moment I'm using
nlminb and optim, both of which allow box constraints on the parameters,
but ideally I'd like to be able to
Hello,
I am having trouble reading an spss file into R. I have reset my
working directory to the folder where this file is stored. This is
what I've typed into R and the error message I received:
+ getwd()
[1] /Users/daviacox/Graduate School/PLS 801
read.spss(norwil.spss)
Error in
Good evening,I am Marta Colombo, student of Politecnico di Milano. I'm
studying Local Regression Techniques such as loess, smoothing splines and
kernel smoothers. Choosing symmetric for the argument family in loess
function it is possible to produce a robust estimate , in function
Viet Nguyen wrote:
Hi all,
I'm trying to make a plot with the function xYplot from package Hmisc in
R. I would like to have minor tick-marks on the axis. This should be a
common simple feature to have but I don't seem to find any discussion on
the topic.
Following is one of the
http://www.maths.lth.se/help/R/.R/library/R.basic/html/robust.smooth.spline.html
Best regards,
Kristel
Marta Colombo wrote:
Good evening,I am Marta Colombo, student of Politecnico di Milano. I'm
studying Local Regression Techniques such as loess, smoothing splines and
kernel smoothers.
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
My ultimate goal is to best fit time series by comparing AICs and BICs
(as in Bayesian) from arima() and nnet().
I looked at the arima.R source code, but I am afraid I do not
understand it.
What I only miss really is the number of parameters p, where:
Note:
As I believe Brian Ripley pointed out in his MASS book, loess may not be as
resistant to outliers (which is one aspect of robustness; robustness of
efficiency is another) as you think. The problem is that it starts off with
LS estimates and these can be so distorted by unusual values that
Colleagues
On occasion, I want to control either tick marks or labels in axes
different from the defaults created with axes=T in the plot
command. If I invoke axes=F and axis(n), I can do so. However,
the axes produced by axis() differ slightly from those produced
within plot. I have
On Mon, 28 Nov 2005, Jean-Luc Fontaine wrote:
My ultimate goal is to best fit time series by comparing AICs and BICs
(as in Bayesian) from arima() and nnet().
Whoa! nnet() does not do maximum likelihood fitting so AIC and BIC are
not even defined.
On the other hand, ?WWWusage has an example
Davia Cox [EMAIL PROTECTED] writes:
Hello,
I am having trouble reading an spss file into R. I have reset my
working directory to the folder where this file is stored. This is
what I've typed into R and the error message I received:
+ getwd()
[1] /Users/daviacox/Graduate School/PLS 801
Greetings,
I am trying to add an extra labled axis in position 3 (top x-axis), with
numbers that do not match up with the existing axes.
Surely this must be possible, and I am just doing it incorectly.
So far I have tried the following:
#make a plot
plot(TIK, type=l, cex=.25, xlim=c(2,32),
On Mon, 2005-11-28 at 13:18 -0800, Dennis Fisher wrote:
Colleagues
On occasion, I want to control either tick marks or labels in axes
different from the defaults created with axes=T in the plot
command. If I invoke axes=F and axis(n), I can do so. However,
the axes produced by
On Mon, 28 Nov 2005, Constantine Tsardounis wrote:
Hello to everyone!...
I would like to ask you if there is a way to extract the known
Durbin-Watson critical values (D_L and D_U - lower and upper limits)
within R, as we do in the DW statistic tables at the end of
Econometrics Textbooks,
Our main US mirror is cran.mirrors.pair.com, AKA cran.us.r-project.org.
Pair.com keeps statistics on traffic on the mirror sites, and I got
all excited when I looked at this page:
http://mirrors.pair.com/pair/stats.html
and saw that CRAN was 5th most popular over the last month, getting more
violating.runs
I read from the news
cran.r-project.org/doc/Rnews/Rnews_2004-1.pdf
that the criteria for the violating is 5 but
1)I cannot find 5 in the code of the function. Where is the 5 ?
2)What is the easiest way to change it ?
3)Is there any more criterias made somewhere ?
Yours
___
You know, this is the first time I've heard of constrOptim.
I actually have a rather complicated, nonlinear boundary expression in
mind, so this function by itself isn't quite what I'm after. Still, I
Duncan asks:
Did we get mentioned somewhere (e.g. Slashdot), or was someone just
experimenting with some automated downloading?
R was mentioned in last week's (I think) O'Reilly newsletter, which
included a link to a short article showing how easy it is to get R to
graph stuff like stock price
___
This would be because quasi(link=logit) doesn't actually fit a logistic
regression. The default variance function for quasi is the identity, not
binomial variance. To emulate a logistic regression, use
Duncan Murdoch [EMAIL PROTECTED] writes:
Our main US mirror is cran.mirrors.pair.com, AKA cran.us.r-project.org.
Pair.com keeps statistics on traffic on the mirror sites, and I got
all excited when I looked at this page:
http://mirrors.pair.com/pair/stats.html
and saw that CRAN was
___
Hm, I should have checked what would happen with binary data and not just
continuous. Using glm with quasi(var=mu(1-mu), link=logit) indeed fails with
NAs/NaNs when y is binary.
--
Hong Ooi
Senior
[EMAIL PROTECTED] writes:
Duncan asks:
Did we get mentioned somewhere (e.g. Slashdot), or was someone just
experimenting with some automated downloading?
R was mentioned in last week's (I think) O'Reilly newsletter, which
included a link to a short article showing how easy it is to get R
Utilizing panel.number and grid allowed me to do all my
desired manipulations - thanks Deepayan!
Roy
Original message
Date: Tue, 22 Nov 2005 13:47:20 -0600
From: Deepayan Sarkar [EMAIL PROTECTED]
Subject: Re: change axis format for different panels in
xyplot in lattice
To: [EMAIL
Have you considered migrating the constraints into the objective
function, then cranking up the penalty for constraint violation once you
have a more or less feasible solution?
spencer graves
Hong Ooi wrote:
Hi all,
Following up on Holger's email last week:
Does anyone know if there exists a library that implements the sensitivity
tests for hidden bias for matched pairs and unmatched groups as proposed in
Rosenbaum's Observational Studies (2002: ch.4)?
Thanks.
Best,
jens
On 29 Nov 2005 01:45:34 +0100, Peter Dalgaard [EMAIL PROTECTED] wrote:
[EMAIL PROTECTED] writes:
Duncan asks:
Did we get mentioned somewhere (e.g. Slashdot), or was someone just
experimenting with some automated downloading?
R was mentioned in last week's (I think) O'Reilly
hi all,
in R, what's the best way to have a rotated ylab in a graph plotted with
either xyplot or xYplot? I tried this but it didn't work.
xyplot(y~x,data.frame(x=1:10,y=runif(10)),ylab=list(srt=90,crt=90,rot=90,label=my
label))
more generally, how do you output a text at an angle in a
Try
library(grid)
xyplot(y~x,data.frame(x=1:10,y=runif(10)), ylab=textGrob(label=my label,
rot=0))
Note in the ?xyplot the xlab/ylab section points to the 'main' parameter
where it defines that a list can be used, however string rotation parameters
are not in the list. The helpfile notes that a
Hi, I have a matrix:
[,1] [,2]
[1,] 11 31
[2,] 44 50
[3,] 23 100
[4,] 90 31
I use plot to draw the four points. Is there any way to label the point? for
insatnce, for (11,31), it is 1, for (44,50), it is 4.
Thanks!
-
Hallo
On 28 Nov 2005 at 21:33, Robert wrote:
Date sent: Mon, 28 Nov 2005 21:33:24 -0800 (PST)
From: Robert [EMAIL PROTECTED]
To: r-help@stat.math.ethz.ch
Subject:[R] label point
Hi, I have a matrix:
[,1] [,2]
[1,] 11 31
See ?text
e.g.
plot(m[,1], m[,2]) # or plot(m)
text(m[,1], m[,2], pos = 3, cex = 0.7) # 3 means above, 0.7 is 70% size
On 11/29/05, Robert [EMAIL PROTECTED] wrote:
Hi, I have a matrix:
[,1] [,2]
[1,] 11 31
[2,] 44 50
[3,] 23 100
[4,] 90 31
I use plot to draw the four points. Is
Tommi Viitanen wrote:
violating.runs
I read from the news
cran.r-project.org/doc/Rnews/Rnews_2004-1.pdf
that the criteria for the violating is 5 but
1)I cannot find 5 in the code of the function. Where is the 5 ?
See ?violating.runs:
violating.runs(object, run.length =
82 matches
Mail list logo