Re: [R] NAs in optim
sum(na.rm=TRUE) works and gives a solution, but in that case I will loose
observations, since if any caw[i,j], mom[i,j] or me[i,j] is a NA, retp[i]
will be a NA in the following
retp[i] - (caw[i,j]+1/24*(b1*mom[i,j] + b2*me[i,j] + b3*btm[i,j]))*ret[i,j]
caw[i,j] is the weight of stock j at date i in a benchmark portfolio; b1,
b2 and b3 are the coefficients to be estimated; mom[i,j], me[i,j] and
btm[i,j] are the characteristics of stock j at date i; and ret[i,j]
is the return on stock j at date i. Rather than estimating one weight for
each stock, I estimate weights as a single function of characteristics that
applies to all 24 stocks.
Prof. Ripley is right; I have NAs in my data using optim, not in optim
itself.
On 1/23/06, Prof Brian Ripley [EMAIL PROTECTED] wrote:
This is NAs in your own code, not in optim! Please use a truthful
subject.
Consider the use of sum(na.rm=TRUE) rather than your inner loop.
On Sun, 22 Jan 2006, Hannu Kahra wrote:
Hi,
I am trying to maximize a utility function using optim. I have a problem
with optim, since some of the values in the caw, mom, me and btm
matrixes in
the code bellow are missing. Is there a handy way just to skip the
missing
values in the loop?
g - 5
retp - NULL
object - function (x)
{
b1 - x[1]
b2 - x[2]
b3 - x[3]
for(i in 1:nrow(ret)){
for(j in 1:ncol(ret)){
retp[i] - (caw[i,j]+1/24*(b1*mom[i,j] + b2*me[i,j] +
b3*btm[i,j]))*ret[i,j]
}
}
util - (1+retp)^(1-g)/(1-g)
return(-sum(util))
}
result - optim(c(2.0,-1.0,3.5
),object,control=list(maxit=500),hessian=TRUE,method=BFGS)
Thank you in advance.
Hannu Kahra
[[alternative HTML version deleted]]
__
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
--
Brian D. Ripley, [EMAIL PROTECTED]
Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel: +44 1865 272861 (self)
1 South Parks Road, +44 1865 272866 (PA)
Oxford OX1 3TG, UKFax: +44 1865 272595
[[alternative HTML version deleted]]
__
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
Re: [R] Latest revision of lme4 requires 'Matrix' = 0.995.2 but that version is not available on CRAN
John Logsdon wrote: I've just hit this problem as well and as I am slumming it on XP at the moment, I don't have the compilation tools to use the .tar.gz version. So please follow that thread and note that people were already working on it for you during the whole weekend! In this case, it does not help to have the tools. The Windows binary package maintainer has had his reasons not to publish the most recent Matrix version. I also notice that the numbering format has changed. Is this intentional? Yes. Uwe Ligges Best wishes John John Logsdon Try to make things as simple Quantex Research Ltd, Manchester UK as possible but not simpler [EMAIL PROTECTED] [EMAIL PROTECTED] +44(0)161 445 4951/G:+44(0)7717758675 www.quantex-research.com On Sat, 21 Jan 2006, Søren Højsgaard wrote: I just updated the packages on my pc (windows xp). When loading lme4 I get library(lme4) Error: package 'Matrix' 0.995-1 was found, but = 0.995.2 is required by 'lme4' 'Matrix' 0.995-1 is indeed installed on my computer, but update.packages() does not capture a never version; and seemingly for good reasons: When looking at CRAN, the new version of Matrix is available - but only as a .tar.gz archive. Two questions 1) How can a new version of lme4 make its way to CRAN when the packages it depends on are not available (that is, in a zip-version)? An answer could be: Buhh, you can just download the .tar.gz archive and then compile it yourself! Surely, that would be possible, but it can not be the intention... 2) When actually trying to compile Matrix, I get lmer.o(.text+0x285f):lmer.c: undefined reference to `atanh' make[3]: *** [Matrix.dll] Error 1 make[2]: *** [srcDynlib] Error 2 make[1]: *** [all] Error 2 make: *** [pkg-Matrix] Error 2 *** Installation of Matrix failed *** Removing 'c:/programs/R/current/library/Matrix' Restoring previous 'c:/programs/R/current/library/Matrix' Can anyone help me on what to do??? Thanks / Søren __ 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 __ 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 __ 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
Re: [R] Run R in background?
Hi, look for BATCH in the manual. (The other friend is called nohup on unix) Detlef On Fri, 20 Jan 2006 13:53:05 -0800 (PST) luk [EMAIL PROTECTED] wrote: According to the manual, a R script can be run in as follows in linux. $ R source(xy.R) Does this mean we have to type R first, and then within R, type: source(xy.R)? Is there other way to run xy.R, say $ R CMD SOURCE xy.R Is there any way to run R in background? Luk - Photo Books. You design it and well bind it! [[alternative HTML version deleted]] __ 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
[R] chm.help in windows
options(chmhelp=TRUE) help(package=fCalendar) does not open teh windows help browser, but help(CalendarData, package=fCalendar) does. Why? A bug? I use R 2.1.1 under Windows2000 Thomas __ 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
[R] Help with plot.svm from e1071
Josh, the problem here is that your code and mine refer to x and non-standard evaluation happens in points(), looking up x in the object supplied to data. So your code will work when you are using, e.g., xx instead of x in the data frame and the call to svm(). I will fix this ASAP, thanks for pointing this out... Cheers, David. -- Hi. I'm trying to plot a pair of intertwined spirals and an svm that separates them. I'm having some trouble. Here's what I tried. library(mlbench) library(e1071) Loading required package: class raw - mlbench.spirals(200,2) spiral - data.frame(class=as.factor(raw$classes), x=raw$x[,1], y=raw$x[,2]) m - svm(class~., data=spiral) plot(m, spiral) Error in -x$index : invalid argument to unary operator So we delve into e1071:::plot.svm. When I run the code in plot.svm everything is fine up until points(formula, data = data[-x$index, ], pch = dataSymbol, col = symbolPalette[colind[-x$index]]) That gives me the same error message, Error in -x$index : invalid argument to unary operator. The weird thing is that I can run either of the those statements in isolation data[-x$index, ] symbolPalette[colind[-x$index]] and neither gives me an error. I looked in the two points functions I can see (points.default and points.formula) but neither calls x$index. I was following along the documentation for plot.svm, which has a simple example (that works) ## a simple example library(MASS) data(cats) m - svm(Sex~., data = cats) plot(m, cats) I don't see what the difference between their example and mine. -- Dr. David Meyer Department of Information Systems and Operations Vienna University of Economics and Business Administration Augasse 2-6, A-1090 Wien, Austria, Europe Fax: +43-1-313 36x746 Tel: +43-1-313 36x4393 HP: http://wi.wu-wien.ac.at/~meyer/ __ 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
[R] FW: aggregating variables with pca
Christian Jones [EMAIL PROTECTED] schrieb am 19.01.06 16:58:58: hello R_team having perfomed a PCA on my fitted model with the function: data- na.omit(dataset) data.pca-prcomp(data,scale =TRUE), I´ve decided to aggregate two variables that are highly correlated. My first question is: How can I combine the two variables into one new predictor? and secondly: How can I predict with the newly created variable in a new dataset? Guess I need the predict and new data command but I´m having problems with the syntax and the help function was not sufficient on this issue. many thanks in advance Christian [[alternative HTML version deleted]] __ 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 Erweitern Sie FreeMail zu einem noch leistungsstarkeren E-Mail-Postfach! [[alternative HTML version deleted]] __ 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
Re: [R] chm.help in windows
Same in R v2.2.1 patched (2006-01-01 r36947) and Rv2.3.0 (2006-01-01 r36947). /Henrik Thomas Steiner wrote: options(chmhelp=TRUE) help(package=fCalendar) does not open teh windows help browser, but help(CalendarData, package=fCalendar) does. Why? A bug? I use R 2.1.1 under Windows2000 Thomas __ 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 __ 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
Re: [R] Making a markov transition matrix
Ajay, On a similar note, there are two other packages as well for similar models: hmm.discnp for hidden Markov models of univariate discrete non-parametric distributions and depmix for hidden Markov models for multivariate data, ie gaussians, multinomials etc, and combinations of these hth, ingmar Ajay--you seem to have gotten your question answered regarding putting your dataframe in the correct format, etc. If you haven't already, you might want to check out the MSM package for multi-state Markov and hidden Markov models in continuous time. It's been quite useful for some of my work regarding estimating Markov chains/matrices and is actively maintained. Thanks, Charles you wrote Folks, I am holding a dataset where firms are observed for a fixed (and small) set of years. The data is in long format - one record for one firm for one point in time. A state variable is observed (a factor). I wish to make a markov transition matrix about the time-series evolution of that state variable. The code below does this. But it's hardcoded to the specific years that I observe. How might one generalise this and make a general function which does this? :-) -ans. set.seed(1001) # Raw data in long format -- raw - data.frame(name=c(f1,f1,f1,f1,f2,f2,f2,f2), year=c(83, 84, 85, 86, 83, 84, 85, 86), state=sample(1:3, 8, replace=TRUE) ) # Shift to wide format -- fixedup - reshape(raw, timevar=year, idvar=name, v.names=state, direction=wide) # Now tediously build up records for an intermediate data structure try - rbind( data.frame(prev=fixedup$state.83, new=fixedup$state.84), data.frame(prev=fixedup$state.84, new=fixedup$state.85), data.frame(prev=fixedup$state.85, new=fixedup$state.86) ) # This is a bad method because it is hardcoded to the specific values # of year. markov - table(destination$prev.state, destination$new.state) -- Ajay Shah http://www.mayin.org/ajayshah [EMAIL PROTECTED] http://ajayshahblog.blogspot.com *(:-? - wizard who doesn't know the answer. [[alternative HTML version deleted]] __ 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 __ 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
Re: [R] chm.help in windows
Henrik Bengtsson wrote: Same in R v2.2.1 patched (2006-01-01 r36947) and Rv2.3.0 (2006-01-01 r36947). /Henrik Thomas Steiner wrote: options(chmhelp=TRUE) help(package=fCalendar) does not open teh windows help browser, but help(CalendarData, package=fCalendar) does. Why? A bug? Because help on a *package* (help(package=fCalendar)) shows a text representation containing well formatted information from the files DESCRIPTION and Index of a package. This is not converted to ANY other help format. Help on a *function* (help(CalendarData, package=fCalendar)) CAN be converted to chm, and this happens for CRAN binary packages for Windows. Uwe Ligges I use R 2.1.1 under Windows2000 Thomas __ 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 __ 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 __ 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
Re: [R] chm.help in windows
Yes, and as documented. `topic' is not an optional argument to help, so help(package=) just gives you a hint about what you could have supplied. On Mon, 23 Jan 2006, Henrik Bengtsson wrote: Same in R v2.2.1 patched (2006-01-01 r36947) and Rv2.3.0 (2006-01-01 r36947). /Henrik Thomas Steiner wrote: options(chmhelp=TRUE) help(package=fCalendar) does not open teh windows help browser, but ^^^ ? I have no idea what the `windows help browser' is, and it is not a term mentioned on the R help page. help(CalendarData, package=fCalendar) does. Why? A bug? I use R 2.1.1 under Windows2000 Thomas -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ 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
[R] R-2.2.1 doesn't compile under cygwin/Win2000
Hello, I've just downloaded the R-2.2.1 source and I'm trying to compile it under cygwin (1.5.19-4). The configure script runs ok, but make generates the following error after a while: - al/include -DHAVE_CONFIG_H -D__NO_MATH_INLINES -g -O2 -c zutil.c -o zutil.o rm -f libz.a ar cr libz.a adler32.o compress.o crc32.o deflate.o gzio.o infback.o inffast.o inflate.o inftrees.o trees.o uncompr.o zutil.o ranlib libz.a make[4]: Leaving directory `/home/Vonkad/R-2.2.1/src/extra/zlib' make[3]: Leaving directory `/home/Vonkad/R-2.2.1/src/extra/zlib' make[3]: Entering directory `/home/Vonkad/R-2.2.1/src/extra/xdr' make[4]: Entering directory `/home/Vonkad/R-2.2.1/src/extra/xdr' making xdr.d from xdr.c making xdr_float.d from xdr_float.c making xdr_mem.d from xdr_mem.c making xdr_stdio.d from xdr_stdio.c make[4]: Leaving directory `/home/Vonkad/R-2.2.1/src/extra/xdr' make[4]: Entering directory `/home/Vonkad/R-2.2.1/src/extra/xdr' gcc -I. -I. -I../../../src/include -I../../../src/include -I/usr/local/inclu de -DHAVE_CONFIG_H -D__NO_MATH_INLINES -g -O2 -c xdr.c -o xdr.o In file included from xdr.c:59: ./rpc/types.h:63: error: conflicting types for 'malloc' ./rpc/types.h:63: error: conflicting types for 'malloc' make[4]: *** [xdr.o] Error 1 make[4]: Leaving directory `/home/Vonkad/R-2.2.1/src/extra/xdr' make[3]: *** [R] Error 2 make[3]: Leaving directory `/home/Vonkad/R-2.2.1/src/extra/xdr' make[2]: *** [R] Error 1 make[2]: Leaving directory `/home/Vonkad/R-2.2.1/src/extra' make[1]: *** [R] Error 1 make[1]: Leaving directory `/home/Vonkad/R-2.2.1/src' make: *** [R] Error 1 -- What could be the cause ? Regards and thanks, David Vonka __ 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
[R] Trees
Hi., I would like to conduct a CHAID tree analysis - Chi-square Automatic Interaction Detector. From what I can make out from MASS, tree, rpart, and a quick search it isn't available as a package. Is that correct or have I missed it? Has anyone an available implementation of it? Thanks Stephen Nana Mail http://mail.nana.co.il - Get Your Free Personal Outlook 2003 Now [[alternative HTML version deleted]] __ 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
Re: [R] R-2.2.1 doesn't compile under cygwin/Win2000
David Vonka wrote: Hello, I've just downloaded the R-2.2.1 source and I'm trying to compile it under cygwin (1.5.19-4). The configure script runs ok, but make generates the following error after a while: - al/include -DHAVE_CONFIG_H -D__NO_MATH_INLINES -g -O2 -c zutil.c -o zutil.o rm -f libz.a ar cr libz.a adler32.o compress.o crc32.o deflate.o gzio.o infback.o inffast.o inflate.o inftrees.o trees.o uncompr.o zutil.o ranlib libz.a make[4]: Leaving directory `/home/Vonkad/R-2.2.1/src/extra/zlib' make[3]: Leaving directory `/home/Vonkad/R-2.2.1/src/extra/zlib' make[3]: Entering directory `/home/Vonkad/R-2.2.1/src/extra/xdr' make[4]: Entering directory `/home/Vonkad/R-2.2.1/src/extra/xdr' making xdr.d from xdr.c making xdr_float.d from xdr_float.c making xdr_mem.d from xdr_mem.c making xdr_stdio.d from xdr_stdio.c make[4]: Leaving directory `/home/Vonkad/R-2.2.1/src/extra/xdr' make[4]: Entering directory `/home/Vonkad/R-2.2.1/src/extra/xdr' gcc -I. -I. -I../../../src/include -I../../../src/include -I/usr/local/inclu de -DHAVE_CONFIG_H -D__NO_MATH_INLINES -g -O2 -c xdr.c -o xdr.o In file included from xdr.c:59: ./rpc/types.h:63: error: conflicting types for 'malloc' ./rpc/types.h:63: error: conflicting types for 'malloc' make[4]: *** [xdr.o] Error 1 make[4]: Leaving directory `/home/Vonkad/R-2.2.1/src/extra/xdr' make[3]: *** [R] Error 2 make[3]: Leaving directory `/home/Vonkad/R-2.2.1/src/extra/xdr' make[2]: *** [R] Error 1 make[2]: Leaving directory `/home/Vonkad/R-2.2.1/src/extra' make[1]: *** [R] Error 1 make[1]: Leaving directory `/home/Vonkad/R-2.2.1/src' make: *** [R] Error 1 -- What could be the cause ? The cause is that you have not read the R Installation and Administration manual. It tells you which tools are required to build R under Windows. In particular, cygwin is unsupported. For the user's convenience, a Windows binary version is also provided on CRAN mirrors. Uwe Ligges Regards and thanks, David Vonka __ 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 __ 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
[R] Making a markov transition matrix - more progress
I solved the problem in one more (and more elegant) way. So here's the
program again.
Where does R stand on the Anderson-Goodman test of 1957? I hunted
around and nobody seems to be doing this in R. Is it that there has
been much progress after 1957 and nobody uses it anymore?
# Problem statement:
#
# You are holding a dataset where firms are observed for a fixed
# (and small) set of years. The data is in long format - one
# record for one firm for one point in time. A state variable is
# observed (a factor).
# You wish to make a markov transition matrix about the time-series
# evolution of that state variable.
set.seed(1001)
# Raw data in long format --
raw - data.frame(name=c(f1,f1,f1,f1,f2,f2,f2,f2),
year=c(83, 84, 85, 86, 83, 84, 85, 86),
state=sample(1:3, 8, replace=TRUE)
)
# Shift to wide format --
fixedup - reshape(raw, timevar=year, idvar=name, v.names=state,
direction=wide)
# Now tediously build up records for an intermediate data structure
tmp - rbind(
data.frame(prev=fixedup$state.83, new=fixedup$state.84),
data.frame(prev=fixedup$state.84, new=fixedup$state.85),
data.frame(prev=fixedup$state.85, new=fixedup$state.86)
)
# This is a bad method because it is hardcoded to the specific values
# of year.
markov - table(tmp$prev, tmp$new)
markov
# Gabor's method --
transition.probabilities - function(D, timevar=year,
idvar=name, statevar=state) {
stage1 - merge(D, cbind(nextt=D[,timevar] + 1, D),
by.x=timevar, by.y=nextt)
v1 - paste(idvar,.x,sep=)
v2 - paste(idvar,.y,sep=)
stage2 - subset(stage1, stage1[,v1]==stage1[,v2])
v1 - paste(statevar,.x,sep=)
v2 - paste(statevar,.y,sep=)
t(table(stage2[,v1], stage2[,v2]))
}
transition.probabilities(raw, timevar=year, idvar=name, statevar=state)
# The new and improved way --
library(msm)
statetable.msm(state, name, data=raw)
--
Ajay Shah http://www.mayin.org/ajayshah
[EMAIL PROTECTED] http://ajayshahblog.blogspot.com
*(:-? - wizard who doesn't know the answer.
__
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
Re: [R] linear contrasts with anova
Dear Marco If you are interested in a comparison of a reference level against each other level (in your case level 1 against level 2 and level 1 against level 3), you can use the summary.lm(), since this is the default contrast (see ?contr.treatment) ar - data.frame(GROUP = factor(rep(1:3, each = 8)), DIP = c(3.0, 3.0, 4.0, 5.0, 6.0, 7.0, 3.0, 2.0, 1.0, 6.0, 5.0, 7.0, 2.0, 3.0, 1.5, 1.7, 17.0, 12.0, 15.0, 16.0, 12.0, 23.0, 19.0, 21.0)) r.aov10 - aov(DIP ~ GROUP, data = ar) anova(r.aov10) summary.lm(r.aov10) As result you will get the comparison GROUP 2 against GROUP 1, denoted by GROUP2 and the comparison GROUP 3 against GROUP 1, denoted by GROUP3. Be careful. In your example you include both GROUP and C1 or C2, respectively in your model. This results in a over parameterized model and you get a warning that not all coefficients have been estimated, due to singularities. It is possible to use other contrasts than contr.treatment, contr.sum, contr.helmert, contr.poly, but then you have to specify the correctly in the model. Regards, Christoph Buser -- Christoph Buser [EMAIL PROTECTED] Seminar fuer Statistik, LEO C13 ETH (Federal Inst. Technology) 8092 Zurich SWITZERLAND phone: x-41-44-632-4673 fax: 632-1228 http://stat.ethz.ch/~buser/ -- Posta Univ. Cagliari writes: I have some doubts about the validity of my procedure to estimeate linear contrasts ina a factorial design. For sake of semplicity, let's imagine a one way ANOVA with three levels. I am interested to test the significance of the difference between the first and third level (called here contrast C1) and between the first and the seconda level (called here contrast C2). I used the following procedure: --- reading data from a text file --- ar -read.table(C:/Programmi/R/myworks/contrasti/cont1.txt,header=TRUE) ar CC GROUP 1 3.0 0 2 3.0 0 3 4.0 0 4 5.0 0 5 6.0 0 6 7.0 0 7 3.0 0 8 2.0 0 9 1.0 1 10 6.0 1 11 5.0 1 12 7.0 1 13 2.0 1 14 3.0 1 15 1.5 1 16 1.7 1 17 17.0 2 18 12.0 2 19 15.0 2 20 16.0 2 21 12.0 2 22 23.0 2 23 19.0 2 24 21.0 2 --- creating a new array of data--- ar-data.frame(GROUP=factor(ar$GROUP),DIP=ar$CC) ar GROUP DIP 1 0 3.0 2 0 3.0 3 0 4.0 4 0 5.0 5 0 6.0 6 0 7.0 7 0 3.0 8 0 2.0 9 1 1.0 10 1 6.0 11 1 5.0 12 1 7.0 13 1 2.0 14 1 3.0 15 1 1.5 16 1 1.7 17 2 17.0 18 2 12.0 19 2 15.0 20 2 16.0 21 2 12.0 22 2 23.0 23 2 19.0 24 2 21.0 --- creating two dummy variables (C1 and C2) for linear contrasts--- ar-data.frame(GROUP=factor(ar$GROUP),C1=factor(ar$GROUP),C2=factor(ar$GROUP),DIP=ar$DIP) ar GROUP C1 C2 DIP 1 0 0 0 3.0 2 0 0 0 3.0 3 0 0 0 4.0 4 0 0 0 5.0 5 0 0 0 6.0 6 0 0 0 7.0 7 0 0 0 3.0 8 0 0 0 2.0 9 1 1 1 1.0 10 1 1 1 6.0 11 1 1 1 5.0 12 1 1 1 7.0 13 1 1 1 2.0 14 1 1 1 3.0 15 1 1 1 1.5 16 1 1 1 1.7 17 2 2 2 17.0 18 2 2 2 12.0 19 2 2 2 15.0 20 2 2 2 16.0 21 2 2 2 12.0 22 2 2 2 23.0 23 2 2 2 19.0 24 2 2 2 21.0 --- selecting the contrast levels--- ar$C1 - C(ar$C1, c(1,0,-1), how.many = 1) ar$C2 - C(ar$C2, c(1,-1,0), how.many = 1) --- contrast analysis of C2 --- r.aov8 -aov(DIP ~ C2 + GROUP , data = ar) anova(r.aov8) Analysis of Variance Table Response: DIP Df Sum Sq Mean Sq F valuePr(F) C2 1 2.102.10 0.2622 0.614 GROUP 1 917.00 917.00 114.3460 5.915e-10 *** Residuals 21 168.418.02 --- Signif. codes: 0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1 --- contrast analysis of C1 --- r.aov9 -aov(DIP ~ C1 + GROUP , data = ar) anova(r.aov9) Analysis of Variance Table Response: DIP Df Sum Sq Mean Sq F valuePr(F) C1 1
[R] Image Processing packages
Hi, I've been looking for Image Processing packages. Thresholding, Edge Filters, Dct, Segmentation, Restoration. I'm aware, that Octave, Matlab etc. would be a good address but then I'm missing the statistical power of R. Does anybody know of packages, projects etc. Comments on wether the use of R for such matters is useful are welcome. Greetings Thomas Kaliwe [[alternative HTML version deleted]] __ 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
[R] Image Processing packages
-Ursprüngliche Nachricht- Von: Thomas Kaliwe [mailto:[EMAIL PROTECTED] Gesendet: Montag, 23. Januar 2006 13:25 An: 'r-help@stat.math.ethz.ch' Betreff: Image Processing packages Hi, Ive been looking for Image Processing packages. Thresholding, Edge Filters, Dct, Segmentation, Restoration. Im aware, that Octave, Matlab etc. would be a good address but then Im missing the statistical power of R. Does anybody know of packages, projects etc. Comments on wether the use of R for such matters is useful are welcome. Greetings Thomas Kaliwe [[alternative HTML version deleted]] __ 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
Re: [R] Image Processing packages
Hello, There are a couple of things for image processing in R (look at pixmap and Rimage, for instance). However, R is *not* a good software for processing images (nor is Matlab, Octave, IDL: they use to have specific packages for image processing and analysis, but resulting applications are way to slow in comparison to dedicated software). A good approach is to mix ImageJ and R, if you are looking for an Open Source solution. You could look at ZooImage for an example application using these two software (analysis of digital zooplankton images, see: http://www.sciviews.org/zooimage). Best, Philippe Grosjean Thomas Kaliwe wrote: Hi, I've been looking for Image Processing packages. Thresholding, Edge Filters, Dct, Segmentation, Restoration. I'm aware, that Octave, Matlab etc. would be a good address but then I'm missing the statistical power of R. Does anybody know of packages, projects etc. Comments on wether the use of R for such matters is useful are welcome. Greetings Thomas Kaliwe [[alternative HTML version deleted]] __ 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 __ 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
[R] design matrix and coefficients
Hey, As a beginner to the limma package I tried to understand how to define a design matrix. I did both experiment examples in the Limma user's Guide manual. Afterwards I wanted to do it with my own data. Here I encounter a few problems. As an example I used four Control samples and 4 treated samples. 1. This is how my target files looks like: filenametreated time.h conc. ctrl_1.cel no240 ctrl_2.cel no240 ctrl_3.cel no240 ctrl_4.cel no240 treat_100_1.cel yes24100 treat_100_2.cel yes24100 treat_1000_3.celyes241000 treat_1000_4.celyes241000 2. I would like to create a design matrix to compare all 4 wt files with all 4 ctrl files. But I also want to see the differences between the two concentrations (100, 1000). I have a problem creating the different coefficients. How do I choose which coefficient to build? I would be happy for any help. I didn't find much information about the limma package and the affymetrix (single-channel) chips. If you can help me looking for general information I'll be also grateful. THX, Assa -- Assa Yeroslaviz Loetzener Str. 15 51373 Leverkusen [[alternative HTML version deleted]] __ 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
Re: [R] Image Processing packages
Hi, Have a look at PerlDL. http://pdl.perl.org/index_en.html It's fast and It's free. Also there's a mailing-list. Far from the activity here, but usually you get your answer. Kare Thomas Kaliwe wrote: -Ursprüngliche Nachricht- Von: Thomas Kaliwe [mailto:[EMAIL PROTECTED] Gesendet: Montag, 23. Januar 2006 13:25 An: 'r-help@stat.math.ethz.ch' Betreff: Image Processing packages Hi, I’ve been looking for Image Processing packages. Thresholding, Edge Filters, Dct, Segmentation, Restoration. I’m aware, that Octave, Matlab etc. would be a good address but then I’m missing the “statistical power” of R. Does anybody know of packages, projects etc. Comments on wether the use of R for such matters is useful are welcome. Greetings Thomas Kaliwe [[alternative HTML version deleted]] __ 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 -- ### Kare Edvardsen [EMAIL PROTECTED] Norwegian Institute for Air Research (NILU) Polarmiljosenteret NO-9296 Tromso http://www.nilu.no Swb. +47 77 75 03 75 Dir. +47 77 75 03 90 Fax. +47 77 75 03 76 Mob. +47 90 74 60 69 ### __ 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
Re: [R] Latest revision of lme4 requires 'Matrix' = 0.995.2 but that version is not available on CRAN
On 1/22/06, John Logsdon [EMAIL PROTECTED] wrote: I've just hit this problem as well and as I am slumming it on XP at the moment, I don't have the compilation tools to use the .tar.gz version. I also notice that the numbering format has changed. Is this intentional? Which numbering format? If you mean the use of 0.995 rather than 0.99 it is because I keep finding changes that need to be made in the underlying format for mixed-effects representations (i.e. mer objects) before a 1.0 release. The current sequence of numbers is 0.99 (99%), 0.995 (99 1/2%), 0.9975 (99 3/4%), 0.99875 (99 7/8%), ... It is a pattern like, but not as inventive as, Donald Knuth's numbering sequence for TeX releases. It has the desirable property of allowing for an infinite number of releases before you need to declare the package to be at release 1.0 There will be at least a 0.9975 series of minor releases (I need to add another two slots to the mer object). __ 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
[R] fractional factorial design in R
Roberto Furlan wrote: Hi, i need to create a fractional factorial design sufficient to estimate the main effects. The factors may have any number of levels, let's say any number from 2 to 6. I've tried to use the library conf.design , but i cannot figure out how to write the code. For example, what is the code for a design with 5 factors (2x3x3x5x2) and only main effects not confounded? thanks in advance! Roberto Furlan University of Turin, Italy Hi Roberto, unfortunately, fractional factorial designs typically require all factors to have the same number of levels. Hence, your 2x3x3x5x2 example is not a simple special case of a fractional factorial design. There are some special plans for mixed level designs, but the conf.design function requires all factors to have the same number of levels, as you can also find in its help: p: The common number of levels for each factor. Must be a prime number. ffDesMatrix from package BHH2 is even worse, since it requires all factors to have 2 levels: k: numeric. The number of 2-levels design factors in the designs. (Note that designs with two level-factors only can accommodate a few four- level factors, by combining two main effects plus their interaction for the three degrees of freedom of the 4-level factor. For doing this, I would recommend to have someone plan the design who really knows what he/she is doing.) Regards, Ulrike __ 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
Re: [R] [Rd] Display an Image on a Plane
Thanks to all for the answers. I needed something quickly for a report so I used Gimp (as proposed by François Pinard) but I will look at the links given by Barry Rowlingson if I want something more fancy. Thanks also to Ben Bolker. Vincent -Original Message- From: François Pinard [mailto:[EMAIL PROTECTED] Sent: Friday, January 20, 2006 6:31 PM To: Barry Rowlingson Cc: Ben Bolker; R-help; Labbe, Vincent (AEREX) Subject: Re: [R] [Rd] Display an Image on a Plane [Barry Rowlingson] [Ben Bolker] [Labbe, Vincent] I am new to R and I would like to display an image on a plane in a 3D plot, i.e. I would like to be able to specify a theta and a phi parameters like in the function persp to display a 2D image on an inclined plane. what do you mean by image exactly? I think once you get into doing fancy visualisations like this then you may find a solution outside of R. [good referrences deleted] Bonjour, Vincent. I'm not fully sure I understand your request, what I get is that you want to transform an image on a plane as if one was looking at it in space, from an angle. If I had this problem, I would probably produce the image using regular R machinery for this like png() or postscript(), then interactively process the result within Gimp, using trapezoidal deformations (I think they call it Perspective transformation). For example, I used this simple trick in the following picture: http://pinard.progiciels-bpi.ca/plaisirs/dessins/cd-back.jpg for the KWIC listing being part of the composition. However, if I needed a precise phi and theta for transformations beyond what trans3d() can offer, I would likely use Python or R for computing the projection of the rectangle enclosing the image, than PIL (Python Imaging Library) for producing that precise trapezoidal deformation. Just sharing ideas, of course. Much likely that if I knew R better, I would use it more fully -- but that's a tautology! :-) -- François Pinard http://pinard.progiciels-bpi.ca __ 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
[R] Sweave: skip if figure exists
Dear RWeavers, to speed up report generation with Sweave, I am looking for an option skipifexists for figures. A named figure chunk should not be executed if the file to be produced already exists. I know that this could be done with hooks, but I want to avoid to re-invent this wheel. Dieter __ 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
Re: [R] Sweave: skip if figure exists
On Mon, 23 Jan 2006 16:41:09 +0100, Dieter Menne (DM) wrote: Dear RWeavers, to speed up report generation with Sweave, I am looking for an option skipifexists for figures. A named figure chunk should not be executed if the file to be produced already exists. I know that this could be done with hooks, but I want to avoid to re-invent this wheel. I have plans to implement something like this for a very long time now, but no code yet. Contributions are of course more than welcome. Best, -- --- Friedrich Leisch Institut für Statistik Tel: (+43 1) 58801 10715 Technische Universität WienFax: (+43 1) 58801 10798 Wiedner Hauptstraße 8-10/1071 A-1040 Wien, Austria http://www.ci.tuwien.ac.at/~leisch __ 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
[R] ordering a data frame to same order as a chr vector
Hi all, I've got a data frame that has an identical column to a chr vector. I would like to use the chr vector to order the rows of the data frame to be identical to the order in the chr vector (the contents of the chr vector are completely identical to one col of the data frame), but this is proving trickier than it sounds.. Any help would be much obliged, -Ken __ 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
Re: [R] Trees
On Mon, 23 Jan 2006, Stephen wrote: Hi., I would like to conduct a CHAID tree analysis - Chi-square Automatic Interaction Detector. From what I can make out from MASS, tree, rpart, and a quick search it isn't available as a package. Is that correct or have I missed it? correct, it is not available out-of-the-box. Has anyone an available implementation of it? if you aim at unbiased variable selection you might want to checkout the `party' package, especially the `ctree' function. Best, Torsten Thanks Stephen Nana Mail http://mail.nana.co.il - Get Your Free Personal Outlook 2003 Now [[alternative HTML version deleted]] __ 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 __ 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
Re: [R] ordering a data frame to same order as a chr vector
Let me clarify the problem a bit further: tv - 1:11108 tdf - data.frame(cbind(11108:1, 22216:11109)) In this example, what I would like to do is re-order the entire tdf data frame based on its first column (since the contents of tdf[,1] are identical to tv, just not necessarily in the same order in my problem, but here obviously the tdf data frame is already ordered the same as tv). I would like to use the vector tv to give tdf the same exact order as tv, based on that first column of tdf which is identical to tv. Thanks, ken __ 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
[R] Creating an R package file
Dear R community, I would like to create my own R package files, but I find some problemm for R versions 1.9. When in previous versions of R I could write a simple text file, to have a functioning file package, now I found that is neccessary to implement also binary copies of the file. I cannot understand, reading from R manuals, how it is the correct procedure to create these binary files. Is there anybody that can help me on this issue? Many thanks, Marco Tommasi [[alternative HTML version deleted]] __ 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
Re: [R] ordering a data frame to same order as a chr vector
This is an FAQ that's not in the official FAQ (I believe). Do RSiteSearch(sort.data.frame) in R and you'll see. Andy From: Ken Termiso Hi all, I've got a data frame that has an identical column to a chr vector. I would like to use the chr vector to order the rows of the data frame to be identical to the order in the chr vector (the contents of the chr vector are completely identical to one col of the data frame), but this is proving trickier than it sounds.. Any help would be much obliged, -Ken __ 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 __ 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
Re: [R] ordering a data frame to same order as a chr vector
probably you are looking for something like the following: dat - data.frame(chr = letters[1:20], x = rnorm(20), y = rnorm(20)) chr.vec - sample(letters[1:20]) 3 dat[match(chr.vec, dat$chr), ] 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 Fax: +32/(0)16/337015 Web: http://www.med.kuleuven.be/biostat/ http://www.student.kuleuven.be/~m0390867/dimitris.htm - Original Message - From: Ken Termiso [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Sent: Monday, January 23, 2006 4:55 PM Subject: [R] ordering a data frame to same order as a chr vector Hi all, I've got a data frame that has an identical column to a chr vector. I would like to use the chr vector to order the rows of the data frame to be identical to the order in the chr vector (the contents of the chr vector are completely identical to one col of the data frame), but this is proving trickier than it sounds.. Any help would be much obliged, -Ken __ 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 Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm __ 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
Re: [R] ordering a data frame to same order as a chr vector
Hi, if I got it right I'd suggest to use match (which would allow you to use also character vectors) So tdf[match(tv,tdf[,1]),] will give you tdf in the same order as tv HIH Ste On Mon, Jan 23, 2006 at 04:09:58PM +, Ken Termiso wrote: KenLet me clarify the problem a bit further: Ken Kentv - 1:11108 Ken Kentdf - data.frame(cbind(11108:1, 22216:11109)) Ken Ken KenIn this example, what I would like to do is re-order the entire tdf data Kenframe based on its first column (since the contents of tdf[,1] are identical Kento tv, just not necessarily in the same order in my problem, but here Kenobviously the tdf data frame is already ordered the same as tv). Ken KenI would like to use the vector tv to give tdf the same exact order as tv, Kenbased on that first column of tdf which is identical to tv. Ken KenThanks, Kenken Ken Ken__ KenR-help@stat.math.ethz.ch mailing list Kenhttps://stat.ethz.ch/mailman/listinfo/r-help KenPLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ 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
Re: [R] White Noise
At 1:38 PM + 1/22/06, Laura Quinn wrote: I'm wanting to create a series of near-identical matrices via the addition of white noise to my starting matrix. Is there a function within R which will allow me to do this? Thank you If the starting matrix is symmetric, see mvrnorm in the MASS package. -- William Revelle http://pmc.psych.northwestern.edu/revelle.html Professor http://personality-project.org/personality.html Department of Psychology http://www.wcas.northwestern.edu/psych/ Northwestern University http://www.northwestern.edu/ __ 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
Re: [R] Creating an R package file
Well, you simply type R CMD INSTALL --build mypackage or R CMD build --binary mypackage in the parent directory of the source package. If you're on Windows, you need to have some tools installed to be able to do that (but you haven't said what OS you're using). Andy From: Posta Univ. Cagliari Dear R community, I would like to create my own R package files, but I find some problemm for R versions 1.9. When in previous versions of R I could write a simple text file, to have a functioning file package, now I found that is neccessary to implement also binary copies of the file. I cannot understand, reading from R manuals, how it is the correct procedure to create these binary files. Is there anybody that can help me on this issue? Many thanks, Marco Tommasi [[alternative HTML version deleted]] __ 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 __ 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
Re: [R] Creating an R package file
If you're on Windows, you need to have some tools installed to be able to do that (but you haven't said what OS you're using). Yes, I forgo tto say that my OS is Windows. Regards, Marco Tommasi __ 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
Re: [R] R-help Digest, Vol 35, Issue 23
summary.aov(aovRes, split=list(interval = list(i1 vs i2 = 1, i2 vs i3 = 2, i3 vs i4 = 3, i4 vs i5 = 4, i5 vs i6 = 5))) try class(aovRes) #- aovlist ! summary.aovlist(aovRes, spit=...) or simply summary(aovRes, spit=...) Hoping this helps, Herwig -- Dr. Herwig Meschke Wissenschaftliche Beratung Hagsbucher Weg 27 D-89150 Laichingen phone +49 7333 210 417 / fax +49 7333 210 418 email [EMAIL PROTECTED] __ 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
Re: [R] Creating an R package file
Posta Univ. Cagliari wrote: Dear R community, I would like to create my own R package files, but I find some problemm for R versions 1.9. When in previous versions of R I could write a simple text file, to have a functioning file package, now I found that is neccessary to implement also binary copies of the file. I cannot understand, reading from R manuals, how it is the correct procedure to create these binary files. Is there anybody that can help me on this issue? The manual Writing R Extensions explains how to write a source package. The manual R Installation and Administration explains how to collect the required tools (your mail header tells us you are on Windows) to perform R CMD INSTALL, R CMD check and R CMD build Uwe Ligges Many thanks, Marco Tommasi [[alternative HTML version deleted]] __ 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 __ 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
[R] lines() in heatmap()
Hello! I looked for help through google and the help-files and spend several hours with trial and error, but didn't find a correct way. It's all about lines in a heatmap to separate different data block from each other to underline the significance of the found clusters! The heatmap is build like that: heatmap(X, Rowv=NA, Colv=NA, symm=TRUE, cexRow=0.3, cexCol=0.3) I switched the dendrograms off, because I don't want the values sorted but in the way, I extracted them from the data. I tried to enter the lines that way: lines(c(14,14),c(0,187), col=green) That should appear as a line parallel to the x-axis, but there was no line at all. I also tried several other ways, which didn't work at all. (The Matrix contains 187 values and is symmetric) Also the line should start and end at the borders of the heatmap, so if there is a parameter to enter that, I would be glad, if you add it. Another short question: Does anybody have an idea, how I could switch the names of my data from the heatmaps right side to it's left side? Thanks for help already, Tobias Zimmer __ 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
Re: [R] fractional factorial design in R
MM == Martin Maechler [EMAIL PROTECTED] on Sat, 21 Jan 2006 09:33:20 +0100 writes: BertG == Berton Gunter [EMAIL PROTECTED] on Fri, 20 Jan 2006 14:15:49 -0800 writes: BertG I'm not sure what you mean by a fractional BertG factorial design here. and Bert was right on target. Please apologize for the following, which I'm now sure Bert knows probably much better than me. MM it's a pretty well known term, in (at least some schools of) MM classical analysis of variance, e.g. MM in the famous Box, Hunter^2 (1987) book which had a 2nd MM edition last year (Wiley), see also Doug Bates's nice account on MM a talk about it, MM http://finzi.psych.upenn.edu/R/Rhelp02a/archive/29768.html MM and the R package BHH2 which is devoted to the book (2nd Ed). MM BHH2 has a function ffDesMatrix() for fractional factorial MM designs, *and* in it's see also section a link to the MM conf.design() function in the package of the same name which MM allows to construct ff designs (via different specifications). MM see e.g, http://finzi.psych.upenn.edu/R/library/BHH2/html/ffDesMatrix.html BertG In general, when dealing with complex designs of the sort you appear to be thinking BertG about, small orthogonal designs don't exist. You BertG might wish to look at the AlgDesign package to BertG generate an efficient design to estimate only main BertG effects. BertG -- Bert Gunter Genentech Non-Clinical Statistics BertG South San Francisco, CA BertG The business of the statistician is to catalyze the BertG scientific learning process. - George E. P. Box MM now, since you have this nice signature, maybe you should MM get the above book? ;-) :-) which was supposed to be something like a joke; given my misreading of Bert's comment, I'm sorry about it. I have no good excuse for my blunder: It was Saturday morning, I had slept well, had had a shower, coffee and breakfast, ... Martin Maechler, ETH Zurich -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Roberto Furlan Sent: Friday, January 20, 2006 12:37 PM To: r-help@stat.math.ethz.ch Subject: [R] fractional factorial design in R Hi, i need to create a fractional factorial design sufficient to estimate the main effects. The factors may have any number of levels, let's say any number from 2 to 6. I've tried to use the library conf.design , but i cannot figure out how to write the code. For example, what is the code for a design with 5 factors (2x3x3x5x2) and only main effects not confounded? thanks in advance! Roberto Furlan University of Turin, Italy __ 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
[R] nlme in R v.2.2.1 and S-Plus v. 7.0
Dear R-Users, I am comparing the nlme package in S-Plus (v. 7.0) and R (v. 2.2.1, nlme package version 3.1-68.1; the lattice, Matrix, and lme4 have also just been updated today, Jan. 23, 2006) on a PC (2.40 GHz Pentium 4 processor and 1 GHz RAM) operating on Windows XP. I am using a real data set with 1,191 units with at most 4 repeated measures per unit (data are incomplete, unbalanced). I use the same code with the same starting values for both programs and obtain slightly different results. I am aware that at this stage my model is far from being well specified for the given data. Nevertheless, I wonder whether one program is more suited than the other to pursue my modeling. Below I included the input + output code, first for S-Plus, than for R. Many thanks and best regards, Paolo Ghisletta #S-Plus #min=4, max=41 logistic4.a - nlme(jugs ~ 4 + 41 / (1 + xmid*exp( -scal*I(occ-1) + u)), fixed=scal+xmid~1, random= u~1 |id, start=c(scal=.2, xmid=155), data=jug, na.action=na.exclude, method=ML) summary(logistic4.a) Nonlinear mixed-effects model fit by maximum likelihood Model: jugs ~ 4 + 41/(1 + xmid * exp( - scal * I(occ - 1) + u)) Data: jug AIC BIClogLik 29595.62 29621.3 -14793.81 Random effects: Formula: u ~ 1 | id u Residual StdDev: 5.162391 3.718887 Fixed effects: scal + xmid ~ 1 Value Std.Error DF t-value p-value scal 4.96970.0823 3339 60.39508 .0001 xmid 683.5634 125.8509 3339 5.43153 .0001 Standardized Within-Group Residuals: Min Q1 MedQ3 Max -10.66576 -0.5039498 0.0002772166 0.1226745 5.453209 Number of Observations: 4531 Number of Groups: 1191 # R #min=4, max=41 logistic4.a - nlme(jugs ~ 4 + 41 / (1 + xmid*exp( -scal*I(occ-1)+ u)), data=jug, fixed=scal+xmid~1, random= u~1 |id, start=c(scal=.2, xmid=155), method=ML, na.action=na.exclude) summary(logistic4.a) Nonlinear mixed-effects model fit by maximum likelihood Model: jugs ~ 4 + 41/(1 + xmid * exp(-scal * I(occ - 1) + u)) Data: jug AIC BIClogLik 29678.11 29703.78 -14835.05 Random effects: Formula: u ~ 1 | id u Residual StdDev: 5.116542 3.767097 Fixed effects: scal + xmid ~ 1 Value Std.Error DF t-value p-value scal 4.9244 0.08121 3339 60.63763 0 xmid 633.6956 115.37512 3339 5.49248 0 Erreur dans dim(x) : aucun slot de nom Dim pour cet objet de la classe correlation [[alternative HTML version deleted]] __ 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
[R] mutlivariate normal and t distributions
Dear R-help list members, I have created a package 'mnormt' with facilities for the multivariate normal and t distributions. The core part is simply an interface to Fortran routines by Alan Genz for computing the integral of two densities over rectangular regions, using an adaptive integration method. Other R functions compute densities and generate random numbers. The starting motivation to write it was the need to have functions which compute the distribution functions in a non-Monte Carlo form, sinse this caused me problems when these probabilities are involved in a minimization problem. For this reason, I could not make use of the CRAN package 'mvtnorm'. Exactly to avoid superposition with the CRAN package, 'mnormt' is made available somehere else, in case other people want to use it. The package 'mnormt' is at http://azzalini.stat.unipd.it/SN/Pkg-mnormt As explained, this is not uploaded to CRAN just to avoid clash with the existing package. However, if it is felt appropriate, I have no objection to upload it to CRAN. Best wishes, Adelchi Azzalini -- Adelchi Azzalini [EMAIL PROTECTED] Dipart.Scienze Statistiche, Università di Padova, Italia tel. +39 049 8274147, http://azzalini.stat.unipd.it/ __ 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
Re: [R] Selecting data frame components by name - do you know ashorter way?
Thank you all very much! The subset function is great! I knew there must be such a very convenient feature in R. I also learned a lot by studying the other ways of selecting data frame components. Greetings Michael __ 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
Re: [R] command in survival package
Thank you guys. But I tried the commands and I still get: aml1-aml[aml$group==1,] aml1 [1] time status x 0 rows (or 0-length row.names) esf.fit - survfit(Surv(aml1$weeks,status) ~ 1) Error in Surv(aml1$weeks, status) : Time variable is not numeric In addition: Warning message: is.na() applied to non-(list or vector) in: is.na(time) which still looks confusing. Or are they should be applied in s-plus instead of R? Thanks a lot! Linda -Original Message- From: Marc Schwartz [mailto:[EMAIL PROTECTED] Sent: Friday, January 20, 2006 4:49 PM To: Thomas Lumley Cc: Linda Lei; R-help@stat.math.ethz.ch Subject: Re: [R] command in survival package On Fri, 2006-01-20 at 15:27 -0800, Thomas Lumley wrote: On Fri, 20 Jan 2006, Linda Lei wrote: Hi there, I have a question about one command sentence when I follow the example in the book of Survival analysis in S: aml1-aml[aml$group==1] If this is really what the book says you should probably complain to the author. However, if it says aml1-aml[aml$group==1,] then you show type that instead. It is hard to be sure, because you don't say where the `aml' data set comes from. It can't be the one in the survival package as this doesn't have a variable called group Thus, I couldn't keep going on the next command: esf.fit-survfit(Surv(aml1,status)~1). This looks implausible as well. I would have expected something like esf.fit-survfit(Surv(time,status)~1, data=aml1) Correct on both accounts Thomas. The text in the book on page 26 appears as Linda posted. However, there is an errata document here: http://www.crcpress.com/e_products/downloads/download.asp?cat_no=C4088 which shows the corrected text as: aml1 - aml[aml$group==1,] # Maintained group only esf.fit - survfit(Surv(aml1$weeks,status) ~ 1) HTH, Marc Schwartz __ 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
[R] (no subject)
Hi there, May I have your help with the following question? I have one output which is like follows: ValidCum Value Frequency Percent Percent percent 15 1 1.01.01.0 17 1 1.01.02.0 Total 100 100 100 Median 42.000 Minimum 15.000 Maximum 55.000 Valid cases 100 Missing cases 0 According to the output, could you help me with what command (in which package) it is used to get the above output? Thank you very much! Linda [[alternative HTML version deleted]] __ 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
[R] Importing QIF files
Has anyone written R code for importing financial QIF files? I know there is an OpenOffice plugin for importing these into a spreadsheet but I found that it omits some records. Thanks, Frank -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University __ 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
[R] Can one write a procedure in R like for instance in Maple ?
Dear R-wizards!
I have been learning on my own how to use this fantastic program.. but I agree
with some people that even with the manuals, the faq and so on.. when you are
sitting fully alone.. progress can be ... slow... very slow indeed.. In fact
sometimes, looking at the solutions provided by some of you- I am just
flabbergasted to the point that I couldn't figure out how to come up with them
myself (sometimes I don't even understand them :-( )
But after spending around three weeks on this, and starting to get fairly
obsessed with it, I decided I shall ask for help,'cause i can't figure out in
the documentation where I should look for this.
In Maple when I want to automatize something boring I write a procedure..
here I am not too sure.. how to bind together a few statements- most of which
are functions... sounds like it would make up a personnal macro..
I am sure I am doing things in such a primitive way that the R-specialists will
wince.. but that's how it goes with beginners!
Set up.
I have 4 fairly large data base with unequal number of lines (around
1200-1500), but identical number of columns (162)-years.
for each column, I construct a data-frame with the corresponding column of DB1,
then from DB2, .. DB4.
This yields a data.frame in which many data are NA- some are real NAs some
others are because I have to take the max of the lines. In any case, the number
of NAs of each of these 4 columns is not identical.
I extract (by sorting and creating 4 new vectors) 4 vectors of variable length
-the relevant and interesting data- to whom I wish to apply some standardized
treatment: that is normality with say Shapiro-Wilks, Levene, etc..
Kruskal-Wallis and probably other things..
I am not showing my tasks because I do not think that I want to bother the
readers with this,, rather ask for general remarks ( you can provide examples
of your own).
For each column I want to write the results in a table.. and append these
resulta for each column.
I was fairly efficient at doing that for a particular column,
but then the simple thought of apply this list of tasks 162 times.. makes
me..
feel that there should be a way to speed up my execution.. (a loop)
However I have not been able to create a super function (or procedure) that
could tie all these statements together in a sensible fashion.. because each
time the data.frame created is generated by a function.. and somehow i still
did not figure out how to write a function of functions
and then maybe a loop do for all values of dates =1:162 this function..
(all the stuff I tried failed, because I was indexing objects that were also
indexed.. I am vague.. but then retracing a 3 weeks of trials and errors errors
errors errors ...\infty :-) is cumbersome)
1. Could anybody give me suggestions where to look and maybe unveil the tricks
of the function of functions ..
ideally I would construct a loop executing a super function.. whose results
would be dumped in a file (write.table) appending each time the result of the
loop i..
but I was not able to construct that...
should I make a wiser use of these apply, tapply, sapply marvels? I dunno.
does something like for (i in 1:G){sapply(b(i),sw)} were b(i) is the dataframe
for column i, and SW is a function (super function-procedure) make sense in R?
I see that there are some fully esoterical paragraphs on things that seem to be
relevant in the manuals.. but.. esoterical.. I cannot make sense of them...
vicious circle..
Thank you in advance for any courageous that would give me a hint..
Christina
__
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
Re: [R] mutlivariate normal and t distributions
Thanks for this. I got stuck some months ago, because I needed to evaluate a certain special normal tail region in at least 10,000 dimensional space, and mvtnorm could not give me adequate numerical precision above about 30 or 35 dimensions. When I get time to return to that project, I will be particularly interested in looking at your code. I would strongly encourage you to submit your package to CRAN. Otherwise it will be harder for people to learn about it and get it. If your package contains functions or other objects with the same names as objects in other packages, that fact could create a conflict, though not insurmountable. If you can make some effort to minimize the potential for name conflicts with other packages, that would be great. However, even without that, I prefer accessibility. Of course, from a user's perspective, it would be best if you and the 'mvtnorm' maintainer (Torsten Hothorn) could develop a consensus on the circumstances under which each algorithm is best and then develop a combined package that makes it easier for users to access the best known method -- and to easily switch between methods, when it may not be clear which is best. However, if you and Torsten don't have time energy for that, I would still encourage you to submit your package to CRAN. Best Wishes, Spencer Graves Adelchi Azzalini wrote: Dear R-help list members, I have created a package 'mnormt' with facilities for the multivariate normal and t distributions. The core part is simply an interface to Fortran routines by Alan Genz for computing the integral of two densities over rectangular regions, using an adaptive integration method. Other R functions compute densities and generate random numbers. The starting motivation to write it was the need to have functions which compute the distribution functions in a non-Monte Carlo form, sinse this caused me problems when these probabilities are involved in a minimization problem. For this reason, I could not make use of the CRAN package 'mvtnorm'. Exactly to avoid superposition with the CRAN package, 'mnormt' is made available somehere else, in case other people want to use it. The package 'mnormt' is at http://azzalini.stat.unipd.it/SN/Pkg-mnormt As explained, this is not uploaded to CRAN just to avoid clash with the existing package. However, if it is felt appropriate, I have no objection to upload it to CRAN. Best wishes, Adelchi Azzalini __ 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
[R] Converting from a dataset to a single column
I have a dataset of 3 columns and 5 rows. temp-data.frame(col1=c(5,10,14,56,7),col2=c(4,2,8,3,34),col3=c(28,4,52,34,67)) I wish to convert this to a single column, with column 1 on top and column 3 on bottom. i.e. 5 10 14 56 7 4 2 8 3 34 28 4 52 34 67 Are there any functions that do this, and that will work well on much larger datasets (e.g. 1000 rows, 6000 columns)? __ 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
Re: [R] Can one write a procedure in R like for instance in Maple ?
1. Have you read the R LANGUAGE DEFINITION in which writing functions is
extensively discussed?
2. One excellent book on R is S PROGRAMMING by Venables and Ripley. I
recommend it highly.
-- Bert Gunter
Genentech Non-Clinical Statistics
South San Francisco, CA
The business of the statistician is to catalyze the scientific learning
process. - George E. P. Box
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of
Baronin P. Storch von
Sent: Monday, January 23, 2006 9:57 AM
To: r-help@stat.math.ethz.ch
Subject: [R] Can one write a procedure in R like for instance
in Maple ?
Dear R-wizards!
I have been learning on my own how to use this fantastic
program.. but I agree with some people that even with the
manuals, the faq and so on.. when you are sitting fully
alone.. progress can be ... slow... very slow indeed.. In
fact sometimes, looking at the solutions provided by some
of you- I am just flabbergasted to the point that I couldn't
figure out how to come up with them myself (sometimes I don't
even understand them :-( )
But after spending around three weeks on this, and starting
to get fairly obsessed with it, I decided I shall ask for
help,'cause i can't figure out in the documentation where I
should look for this.
In Maple when I want to automatize something boring I write a
procedure..
here I am not too sure.. how to bind together a few
statements- most of which are functions... sounds like it
would make up a personnal macro..
I am sure I am doing things in such a primitive way that the
R-specialists will wince.. but that's how it goes with beginners!
Set up.
I have 4 fairly large data base with unequal number of lines
(around 1200-1500), but identical number of columns (162)-years.
for each column, I construct a data-frame with the
corresponding column of DB1, then from DB2, .. DB4.
This yields a data.frame in which many data are NA- some are
real NAs some others are because I have to take the max of
the lines. In any case, the number of NAs of each of these 4
columns is not identical.
I extract (by sorting and creating 4 new vectors) 4 vectors
of variable length
-the relevant and interesting data- to whom I wish to apply
some standardized treatment: that is normality with say
Shapiro-Wilks, Levene, etc.. Kruskal-Wallis and probably
other things..
I am not showing my tasks because I do not think that I want
to bother the readers with this,, rather ask for general
remarks ( you can provide examples of your own).
For each column I want to write the results in a table.. and
append these resulta for each column.
I was fairly efficient at doing that for a particular column,
but then the simple thought of apply this list of tasks
162 times.. makes me..
feel that there should be a way to speed up my
execution.. (a loop)
However I have not been able to create a super function (or
procedure) that could tie all these statements together in a
sensible fashion.. because each time the data.frame created
is generated by a function.. and somehow i still did not
figure out how to write a function of functions
and then maybe a loop do for all values of dates =1:162 this
function..
(all the stuff I tried failed, because I was indexing objects
that were also indexed.. I am vague.. but then retracing a 3
weeks of trials and errors errors errors errors ...\infty :-)
is cumbersome)
1. Could anybody give me suggestions where to look and maybe
unveil the tricks of the function of functions ..
ideally I would construct a loop executing a super function..
whose results would be dumped in a file (write.table)
appending each time the result of the loop i..
but I was not able to construct that...
should I make a wiser use of these apply, tapply, sapply
marvels? I dunno.
does something like for (i in 1:G){sapply(b(i),sw)} were
b(i) is the dataframe for column i, and SW is a function
(super function-procedure) make sense in R?
I see that there are some fully esoterical paragraphs on
things that seem to be relevant in the manuals.. but..
esoterical.. I cannot make sense of them... vicious circle..
Thank you in advance for any courageous that would give me a hint..
Christina
__
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
__
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
Re: [R] Converting from a dataset to a single column
r user [EMAIL PROTECTED] writes: I have a dataset of 3 columns and 5 rows. temp-data.frame(col1=c(5,10,14,56,7),col2=c(4,2,8,3,34),col3=c(28,4,52,34,67)) I wish to convert this to a single column, with column 1 on top and column 3 on bottom. i.e. 5 10 14 56 7 4 2 8 3 34 28 4 52 34 67 Are there any functions that do this, and that will work well on much larger datasets (e.g. 1000 rows, 6000 columns)? unlist(temp,use.names=FALSE) Did you really mean column (as opposed to vector?), if so, matrix(unlist(temp,use.names=FALSE)) -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ 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
Re: [R] command in survival package
On Mon, 23 Jan 2006, Linda Lei wrote: Thank you guys. But I tried the commands and I still get: aml1-aml[aml$group==1,] aml1 [1] time status x 0 rows (or 0-length row.names) esf.fit - survfit(Surv(aml1$weeks,status) ~ 1) Error in Surv(aml1$weeks, status) : Time variable is not numeric In addition: Warning message: is.na() applied to non-(list or vector) in: is.na(time) which still looks confusing. Or are they should be applied in s-plus instead of R? You *still* haven't said where the aml dataset comes from, but as I said before, it isn't the same as the one built in to R, so you need to load it somehow. The one in R has columns called time, status and x; you appear to want one with columns weeks,status, and group, and with group being numeric rather than factor. -thomas __ 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
[R] cluster plot for cmeans cluster result
Hi, I am trying to make a plot similar to figure 2 on page 318 of the finding groups in data book by kaufman / rousseeuw. I found plot.partition and clusplot but I don't get them to work from the results returned from a cmeans() clustering. How do I have to transform the parameters? Thanks a million, Werner - [[alternative HTML version deleted]] __ 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
[R] R: fractional factorial design in R
Hi! thanks for your response! unfortunately, fractional factorial designs typically require all factors to have the same number of levels. Hence, your 2x3x3x5x2 example is not a simple special case of a fractional factorial design. There are some special plans for mixed level designs, but the conf.design function requires all factors to have the same number of levels, as you can also find in its help: p: The common number of levels for each factor. Must be a prime number. ffDesMatrix from package BHH2 is even worse, since it requires all factors to have 2 levels: k: numeric. The number of 2-levels design factors in the designs. I've tried both ffDesMatrix and conf.design and i realized that they cannot help me for the problem above. At the moment, I am using an SPSS function (orthoplan) for my needs. It provides factorial design with only main effects (small orthogonal designs). Since SPSS is very expensive (in particular with this add-on), I would like to use R as for all my other projects and research activity. Do you know any other way to produce these designs in R? Thanks in advance, Roberto Furlan University of Turin, Italy La mia Cartella di Posta in Arrivo è protetta con SPAMfighter 188 messaggi contenenti spam sono stati bloccati con successo. Scarica gratuitamente SPAMfighter! __ 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
Re: [R] Converting from a dataset to a single column
temp-data.frame(col1=c(5,10,14,56,7),col2=c(4,2,8,3,34),col3=c(28,4,52,34,67)) temp col1 col2 col3 154 28 2 1024 3 148 52 4 563 34 57 34 67 as.numeric(as.matrix(temp)) [1] 5 10 14 56 7 4 2 8 3 34 28 4 52 34 67 Whether this works well enough: temp - as.data.frame(matrix(1:(1000*6000), nr=1000)) dim(temp) [1] 1000 6000 date() ; num - as.numeric(as.matrix(temp)) ; date() [1] Mon Jan 23 19:40:25 2006 [1] Mon Jan 23 19:40:25 2006 length(num) [1] 600 Gabor On Mon, Jan 23, 2006 at 09:49:40AM -0800, r user wrote: I have a dataset of 3 columns and 5 rows. temp-data.frame(col1=c(5,10,14,56,7),col2=c(4,2,8,3,34),col3=c(28,4,52,34,67)) I wish to convert this to a single column, with column 1 on top and column 3 on bottom. i.e. 5 10 14 56 7 4 2 8 3 34 28 4 52 34 67 Are there any functions that do this, and that will work well on much larger datasets (e.g. 1000 rows, 6000 columns)? __ 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 -- Csardi Gabor [EMAIL PROTECTED]MTA RMKI, ELTE TTK __ 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
Re: [R] Converting from a dataset to a single column
?unlist temp-data.frame (col1=c(5,10,14,56,7),col2=c(4,2,8,3,34),col3=c(28,4,52,34,67)) temp col1 col2 col3 154 28 2 1024 3 148 52 4 563 34 57 34 67 unlist(temp) col11 col12 col13 col14 col15 col21 col22 col23 col24 col25 col31 col32 col33 col34 col35 5101456 7 4 2 8 33428 4 523467 On 1/23/06, r user [EMAIL PROTECTED] wrote: I have a dataset of 3 columns and 5 rows. temp-data.frame (col1=c(5,10,14,56,7),col2=c(4,2,8,3,34),col3=c(28,4,52,34,67)) I wish to convert this to a single column, with column 1 on top and column 3 on bottom. i.e. 5 10 14 56 7 4 2 8 3 34 28 4 52 34 67 Are there any functions that do this, and that will work well on much larger datasets (e.g. 1000 rows, 6000 columns)? __ 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 -- Jim Holtman Cincinnati, OH +1 513 247 0281 What the problem you are trying to solve? [[alternative HTML version deleted]] __ 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
Re: [R] Image Processing packages
[EMAIL PROTECTED] wrote: Philippe, I am trying to get there but I keep on receiving a blank file after 5 minutes, is there something wrong with the site? H.Ghezzo McGill University Montreal - Canada Well, I am trying myself. Indded, it seems that my server is down, or very busy. I will look at this tomorrow. Best, Philippe Grosjean Quoting Philippe Grosjean [EMAIL PROTECTED]: Hello, There are a couple of things for image processing in R (look at pixmap and Rimage, for instance). However, R is *not* a good software for processing images (nor is Matlab, Octave, IDL: they use to have specific packages for image processing and analysis, but resulting applications are way to slow in comparison to dedicated software). A good approach is to mix ImageJ and R, if you are looking for an Open Source solution. You could look at ZooImage for an example application using these two software (analysis of digital zooplankton images, see: http://www.sciviews.org/zooimage). Best, Philippe Grosjean Thomas Kaliwe wrote: Hi, I've been looking for Image Processing packages. Thresholding, Edge Filters, Dct, Segmentation, Restoration. I'm aware, that Octave, Matlab etc. would be a good address but then I'm missing the statistical power of R. Does anybody know of packages, projects etc. Comments on wether the use of R for such matters is useful are welcome. Greetings Thomas Kaliwe [[alternative HTML version deleted]] __ 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 __ 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 __ 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
Re: [R] fractional factorial design in R
At the moment, I am using an SPSS function (orthoplan) for my needs. It provides factorial design with only main effects (small orthogonal designs). Since SPSS is very expensive (in particular with this add-on), I would like to use R as for all my other projects and research activity. Yes, you're right. For, say, a 3 x 5 design, one can do this in as few as 7 runs -- but only in general by some version of one-factor-at-a-time (OFAT) designs, which are inefficient. It is easy, via, say model.matrix() to write a general function to produce these. But I think it's a bad idea; more efiicient algorithmic designs are better, IMO, which is why I suggested AlgDesign. You and others are free to disagree, of course. Cheers, Bert Do you know any other way to produce these designs in R? Thanks in advance, Roberto Furlan University of Turin, Italy La mia Cartella di Posta in Arrivo è protetta con SPAMfighter 188 messaggi contenenti spam sono stati bloccati con successo. Scarica gratuitamente SPAMfighter! __ 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
Re: [R] Latest revision of lme4 requires 'Matrix' = 0.995.2 but that version is not available on CRAN
Doug and list No, the change as reported on my XP PC was Matrix package 0.995-1 was found but lme4 requires = 0.995.2. The format change was from a dash to a dot. Maybe a few more would spell SOS! But it's the sort of thing where sometimes even the geniuses very close to the work may read the string they think they wrote by gestalt. As long as it is what was intended and works, it doesn't matter. But what about working in logits. Each new mini-version would have a constant amount of logit added, ultimately to be changed to the next release...:-)) Best wishes to all John John Logsdon Try to make things as simple Quantex Research Ltd, Manchester UK as possible but not simpler [EMAIL PROTECTED] [EMAIL PROTECTED] +44(0)161 445 4951/G:+44(0)7717758675 www.quantex-research.com On Mon, 23 Jan 2006, Douglas Bates wrote: On 1/22/06, John Logsdon [EMAIL PROTECTED] wrote: I've just hit this problem as well and as I am slumming it on XP at the moment, I don't have the compilation tools to use the .tar.gz version. I also notice that the numbering format has changed. Is this intentional? Which numbering format? If you mean the use of 0.995 rather than 0.99 it is because I keep finding changes that need to be made in the underlying format for mixed-effects representations (i.e. mer objects) before a 1.0 release. The current sequence of numbers is 0.99 (99%), 0.995 (99 1/2%), 0.9975 (99 3/4%), 0.99875 (99 7/8%), ... It is a pattern like, but not as inventive as, Donald Knuth's numbering sequence for TeX releases. It has the desirable property of allowing for an infinite number of releases before you need to declare the package to be at release 1.0 There will be at least a 0.9975 series of minor releases (I need to add another two slots to the mer object). __ 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
Re: [R] lines() in heatmap()
Hi kaoskrew.de wrote: Hello! I looked for help through google and the help-files and spend several hours with trial and error, but didn't find a correct way. It's all about lines in a heatmap to separate different data block from each other to underline the significance of the found clusters! The heatmap is build like that: heatmap(X, Rowv=NA, Colv=NA, symm=TRUE, cexRow=0.3, cexCol=0.3) I switched the dendrograms off, because I don't want the values sorted but in the way, I extracted them from the data. I tried to enter the lines that way: lines(c(14,14),c(0,187), col=green) That should appear as a line parallel to the x-axis, but there was no line at all. I also tried several other ways, which didn't work at all. (The Matrix contains 187 values and is symmetric) Take a look at the 'add.expr' argument to heatmap. Here's a simple example: x - as.matrix(mtcars) rc - rainbow(nrow(x), start=0, end=.3) cc - rainbow(ncol(x), start=0, end=.3) hv - heatmap(x, col = cm.colors(256), scale=column, RowSideColors = rc, ColSideColors = cc, margin=c(5,10), xlab = specification variables, ylab= Car Models, main = heatmap(Mtcars data, ..., scale = \column\), # IMPORTANT BIT HERE add.expr = abline(h=5, v=2)) Paul Also the line should start and end at the borders of the heatmap, so if there is a parameter to enter that, I would be glad, if you add it. Another short question: Does anybody have an idea, how I could switch the names of my data from the heatmaps right side to it's left side? Thanks for help already, Tobias Zimmer __ 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 -- Dr Paul Murrell Department of Statistics The University of Auckland Private Bag 92019 Auckland New Zealand 64 9 3737599 x85392 [EMAIL PROTECTED] http://www.stat.auckland.ac.nz/~paul/ __ 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
[R] In which application areas is R used?
If anyone has a list of application areas where there is extensive use of R, I'd like to hear of it. My current short list is: Bioinformatics Epidemiology Geophysics Agriculture and crop science John Maindonald Mathematical Sciences Institute, Australian National University. [EMAIL PROTECTED] __ 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
[R] simple problem
Hi, look this: summary(família) Anacardiaceae Annonaceae Bombacaceae Cecropiaceae 2413 Chrysobalanaceae ClusiaceaeEuphorbiacaea Fabacea 1143 Fabaceae Flacourtiaceae Humiriaceaeindeterminada 17212 LauraceaeMalpighiaceaeMeliaceae Mimosaceae 4461 Moracea MoraceaeMyrtaceaeNyctaginaceae 1121 OlacaceaeRubiaceae SapotaceaeViolaceae 2131 summary(família)==17 Anacardiaceae Annonaceae Bombacaceae Cecropiaceae FALSEFALSEFALSEFALSE Chrysobalanaceae ClusiaceaeEuphorbiacaea Fabacea FALSEFALSEFALSEFALSE Fabaceae Flacourtiaceae Humiriaceaeindeterminada TRUEFALSEFALSEFALSE LauraceaeMalpighiaceaeMeliaceae Mimosaceae FALSEFALSEFALSEFALSE Moracea MoraceaeMyrtaceaeNyctaginaceae FALSEFALSEFALSEFALSE OlacaceaeRubiaceae SapotaceaeViolaceae FALSEFALSEFALSEFALSE família[summary(família)==17] [1] Fabaceae Rubiaceae Meliaceae 24 Levels: Anacardiaceae Annonaceae Bombacaceae ... Violaceae Why it dont work? Only Fabaceae == 17. Thanks Ronaldo -- | // | \\ [***] | ( õ õ ) [Ronaldo Reis Júnior] | V [UFV/DBA-Entomologia] |/ \ [36570-000 Viçosa - MG ] | /(.''`.)\ [Fone: 31-3899-4007 ] | /(: :' :)\ [EMAIL PROTECTED]] |/ (`. `'` ) \[ICQ#: 5692561 | LinuxUser#: 205366 ] |( `- ) [***] | _/ \_Powered by GNU/Debian Woody/Sarge __ 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
Re: [R] command in survival package
On Mon, 2006-01-23 at 10:52 -0800, Thomas Lumley wrote: On Mon, 23 Jan 2006, Linda Lei wrote: Thank you guys. But I tried the commands and I still get: aml1-aml[aml$group==1,] aml1 [1] time status x 0 rows (or 0-length row.names) esf.fit - survfit(Surv(aml1$weeks,status) ~ 1) Error in Surv(aml1$weeks, status) : Time variable is not numeric In addition: Warning message: is.na() applied to non-(list or vector) in: is.na(time) which still looks confusing. Or are they should be applied in s-plus instead of R? You *still* haven't said where the aml dataset comes from, but as I said before, it isn't the same as the one built in to R, so you need to load it somehow. The one in R has columns called time, status and x; you appear to want one with columns weeks,status, and group, and with group being numeric rather than factor. -thomas I don't have the book with me (it's at home), but I suspect that the problem here is that the 'aml' dataset provided at the aforementioned web site: http://www.crcpress.com/e_products/downloads/download.asp?cat_no=C4088 which is to be used with the code under discussion, was more than likely not imported into an R session by Linda. Since one needs to do a: library(survival) to utilize the R code examples, that loads that package's 'aml' dataset, resulting in: aml[aml$group==1,] [1] time status x 0 rows (or 0-length row.names) since there is no 'group' column in the built in 'aml' dataset as Thomas points out. There is such a structure to the authors' version of the dataset: str(read.table(aml.txt, header = TRUE)) `data.frame': 23 obs. of 3 variables: $ weeks : num 9 13 13 18 23 28 31 34 45 48 ... $ group : num 1 1 1 1 1 1 1 1 1 1 ... $ status: num 1 1 0 1 1 0 1 1 0 1 ... Thus: aml - read.table(aml.txt, header = TRUE) (aml1 - aml[aml$group==1,]) weeks group status 1 9 1 1 2 13 1 1 3 13 1 0 4 18 1 1 5 23 1 1 6 28 1 0 7 31 1 1 8 34 1 1 9 45 1 0 1048 1 1 11 161 1 0 This bring us to the still remaining error in the authors' survival code, which is not fully corrected in the authors' online errata: esf.fit - survfit(Surv(aml1$weeks,status) ~ 1) Error in Surv(aml1$weeks, status) : object status not found Thus, something like one of the following should be used instead: esf.fit - survfit(Surv(aml1$weeks, aml1$status) ~ 1) esf.fit - with(aml1, survfit(Surv(weeks, status) ~ 1)) summary(esf.fit) Call: survfit(formula = Surv(aml1$weeks, aml1$status) ~ 1) time n.risk n.event survival std.err lower 95% CI upper 95% CI 9 11 10.909 0.0867 0.75411.000 13 10 10.818 0.1163 0.61921.000 18 8 10.716 0.1397 0.48841.000 23 7 10.614 0.1526 0.37690.999 31 5 10.491 0.1642 0.25490.946 34 4 10.368 0.1627 0.15490.875 48 2 10.184 0.1535 0.03590.944 I'll pass on a note to the authors, whose e-mail addresses I have located via Google. HTH, Marc Schwartz __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] In which application areas is R used?
On Tue, 24 Jan 2006 06:35:00 +1100, John Maindonald wrote: If anyone has a list of application areas where there is extensive use of R, I'd like to hear of it. My current short list is: Bioinformatics Epidemiology Geophysics Agriculture and crop science Cheminformatics and QSAR Rajarshi Guha [EMAIL PROTECTED] http://jijo.cjb.net __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Sample rows in data frame by subsets
Hi, I need to resample rows in a data frame by subsets L3 - LETTERS[1:3] d - data.frame(cbind(x=1, y=1:10), fac=sample(L3, 10, repl=TRUE)) x y fac 1 1 1 A 2 1 2 A 3 1 3 A 4 1 4 A 5 1 5 C 6 1 6 C 7 1 7 B 8 1 8 A 9 1 9 C 10 1 10 A I have seen this used to sample rows with replacement d[sample(nrow(d), replace=T), ] x y fac 7 1 7 B 2 1 2 A 1 1 1 A 3 1 3 A 2.1 1 2 A 10 1 10 A 8 1 8 A 9 1 9 C 1.1 1 1 A 8.1 1 8 A but I would like to sample based on the original number in fac summary(d$fac) A B C 6 1 3 rbind(subset(d, fac==A)[sample(6, replace=T), ], subset(d, fac==B)[sample(1, replace=T), ], subset(d, fac==C)[sample(3, replace=T), ] ) x y fac 2 1 2 A 3 1 3 A 3.1 1 3 A 1 1 1 A 10 1 10 A 1.1 1 1 A 7 1 7 B 5 1 5 C 6 1 6 C 5.1 1 5 C Is there an easy way to do this in one step or with a short function? I have lots of dataframes to resample. Thanks, Chris -- - Chris Stubben Los Alamos National Lab BioScience Division MS M888 Los Alamos, NM 87545 __ 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
Re: [R] simple problem
From: Ronaldo Reis-Jr. Hi, look this: summary(família) Anacardiaceae Annonaceae Bombacaceae Cecropiaceae 2413 Chrysobalanaceae ClusiaceaeEuphorbiacaea Fabacea 1143 Fabaceae Flacourtiaceae Humiriaceaeindeterminada 17212 LauraceaeMalpighiaceaeMeliaceae Mimosaceae 4461 Moracea MoraceaeMyrtaceaeNyctaginaceae 1121 OlacaceaeRubiaceae SapotaceaeViolaceae 2131 summary(família)==17 Anacardiaceae Annonaceae Bombacaceae Cecropiaceae FALSEFALSEFALSEFALSE Chrysobalanaceae ClusiaceaeEuphorbiacaea Fabacea FALSEFALSEFALSEFALSE Fabaceae Flacourtiaceae Humiriaceaeindeterminada TRUEFALSEFALSEFALSE LauraceaeMalpighiaceaeMeliaceae Mimosaceae FALSEFALSEFALSEFALSE Moracea MoraceaeMyrtaceaeNyctaginaceae FALSEFALSEFALSEFALSE OlacaceaeRubiaceae SapotaceaeViolaceae FALSEFALSEFALSEFALSE família[summary(família)==17] [1] Fabaceae Rubiaceae Meliaceae 24 Levels: Anacardiaceae Annonaceae Bombacaceae ... Violaceae Why it dont work? Only Fabaceae == 17. If you look at length(familia) and length(summary(familia) == 17) perhaps you'll see the light... Andy Thanks Ronaldo -- | // | \\ [***] | ( õ õ ) [Ronaldo Reis Júnior] | V [UFV/DBA-Entomologia] |/ \ [36570-000 Viçosa - MG ] | /(.''`.)\ [Fone: 31-3899-4007 ] | /(: :' :)\ [EMAIL PROTECTED]] |/ (`. `'` ) \[ICQ#: 5692561 | LinuxUser#: 205366 ] |( `- ) [***] | _/ \_Powered by GNU/Debian Woody/Sarge __ 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 __ 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
[R] R: fractional factorial design in R
Yes, you're right. For, say, a 3 x 5 design, one can do this in as few as 7 runs -- but only in general by some version of one-factor-at-a-time (OFAT) designs, which are inefficient. It is easy, via, say model.matrix() to write a general function to produce these. But I think it's a bad idea; more efiicient algorithmic designs are better, IMO, which is why I suggested AlgDesign. You and others are free to disagree, of course. Hi Bert, thanks for your suggestion. However, let us say that i need a 2x2x2x3x3x3 design, which should not be too hard. I've loaded AlgDesign, and i am aware now that gen.factorial allows me to create a full desing. But how to create a main-effects-only factorial design (orthogonal)? I am still not able to produce what i need. The function model.matrix.formula is not very clear... :( Could you please indicate which syntax should i use? I'd really appreciate your help. Thanks in advance, Roberto Furlan University of Turin, Italy La mia Cartella di Posta in Arrivo è protetta con SPAMfighter 188 messaggi contenenti spam sono stati bloccati con successo. Scarica gratuitamente SPAMfighter! __ 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
[R] In which application areas is R used?
Population biology It's dominated by matlab, but I see R used more and more. http://popstudies.stanford.edu/summer_course.html Chris -- - Chris Stubben Los Alamos National Lab BioScience Division MS M888 Los Alamos, NM 87545 __ 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
Re: [R] Can one write a procedure in R like for instance in Maple ?
Thomas Lumley has some notes that might be very helpful for you:
http://faculty.washington.edu/tlumley/Rcourse/
Deepayan Sarkar also has some notes that might be of interest:
http://www.cs.wisc.edu/~deepayan/SIBS2005/
Andy
From: Baronin P. Storch von
Dear R-wizards!
I have been learning on my own how to use this fantastic
program.. but I agree with some people that even with the
manuals, the faq and so on.. when you are sitting fully
alone.. progress can be ... slow... very slow indeed.. In
fact sometimes, looking at the solutions provided by some
of you- I am just flabbergasted to the point that I couldn't
figure out how to come up with them myself (sometimes I don't
even understand them :-( )
But after spending around three weeks on this, and starting
to get fairly obsessed with it, I decided I shall ask for
help,'cause i can't figure out in the documentation where I
should look for this.
In Maple when I want to automatize something boring I write a
procedure..
here I am not too sure.. how to bind together a few
statements- most of which are functions... sounds like it
would make up a personnal macro..
I am sure I am doing things in such a primitive way that the
R-specialists will wince.. but that's how it goes with beginners!
Set up.
I have 4 fairly large data base with unequal number of lines
(around 1200-1500), but identical number of columns (162)-years.
for each column, I construct a data-frame with the
corresponding column of DB1, then from DB2, .. DB4.
This yields a data.frame in which many data are NA- some are
real NAs some others are because I have to take the max of
the lines. In any case, the number of NAs of each of these 4
columns is not identical.
I extract (by sorting and creating 4 new vectors) 4 vectors
of variable length
-the relevant and interesting data- to whom I wish to apply
some standardized treatment: that is normality with say
Shapiro-Wilks, Levene, etc.. Kruskal-Wallis and probably
other things..
I am not showing my tasks because I do not think that I want
to bother the readers with this,, rather ask for general
remarks ( you can provide examples of your own).
For each column I want to write the results in a table.. and
append these resulta for each column.
I was fairly efficient at doing that for a particular column,
but then the simple thought of apply this list of tasks
162 times.. makes me..
feel that there should be a way to speed up my
execution.. (a loop)
However I have not been able to create a super function (or
procedure) that could tie all these statements together in a
sensible fashion.. because each time the data.frame created
is generated by a function.. and somehow i still did not
figure out how to write a function of functions
and then maybe a loop do for all values of dates =1:162 this
function..
(all the stuff I tried failed, because I was indexing objects
that were also indexed.. I am vague.. but then retracing a 3
weeks of trials and errors errors errors errors ...\infty :-)
is cumbersome)
1. Could anybody give me suggestions where to look and maybe
unveil the tricks of the function of functions ..
ideally I would construct a loop executing a super function..
whose results would be dumped in a file (write.table)
appending each time the result of the loop i..
but I was not able to construct that...
should I make a wiser use of these apply, tapply, sapply
marvels? I dunno.
does something like for (i in 1:G){sapply(b(i),sw)} were
b(i) is the dataframe for column i, and SW is a function
(super function-procedure) make sense in R?
I see that there are some fully esoterical paragraphs on
things that seem to be relevant in the manuals.. but..
esoterical.. I cannot make sense of them... vicious circle..
Thank you in advance for any courageous that would give me a hint..
Christina
__
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
__
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
[R] Easy, Robust and Stable GUI???
I know that this isn't really a R help question, but I am a psychology student at TRU (tru.ca) and my psych department is going to be switching statistical software in the near future. I thought this might be a good oppertunity to advocate for open source if an acceptable option is available. I have looked around a bit and R seems to be the most stable and mature (not to mention powerful) open source statistical program going. The only downfall is that the school has been using spss for years and would demand a similarly user friendly GUI based statistical program to replace it. I have looked at a few of the R guis and most of them look like they are just command line interfaces in pretty desktop windows and not really a gui like spss. If anyone knows of any stable, userfriendly and robust guis for R that would be similar to using spss please let me know, as I would love for my school to start embracing open source software. Thanks Pat -- View this message in context: http://www.nabble.com/Easy%2C-Robust-and-Stable-GUI--t982193.html#a2543480 Sent from the R help forum at Nabble.com. [[alternative HTML version deleted]] __ 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
Re: [R] R: fractional factorial design in R
In general, a main effects design need not be orthogonal -- the main effects merely need to be estimable. The trick is to estimate them with good efficiency, etc. I think you need to consult a local statistician for help to understand what these statistical concepts mean. In your example you could cross the 2^(3-1) with the 3^(3-1) to produce an orthogonal design to estimate main effects. But of course that's 72 runs, which I don't think you would consider small. As a previous poster commented, there are orthogonal mixed level arrays (Addleman, Kempthorne Youden -designs are a couple of phrases to try googling on) which stem from the 1960's. I doubt that, in general, they would satisfy your needs. I have not used the AlgDesign package myself. I suggest you direct questions about it to the author/maintainer, Bob Wheeler. -- Bert Gunter Genentech Non-Clinical Statistics South San Francisco, CA The business of the statistician is to catalyze the scientific learning process. - George E. P. Box -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of [EMAIL PROTECTED] Sent: Monday, January 23, 2006 12:20 PM To: Berton Gunter; [EMAIL PROTECTED]; r-help@stat.math.ethz.ch Subject: [R] R: fractional factorial design in R Yes, you're right. For, say, a 3 x 5 design, one can do this in as few as 7 runs -- but only in general by some version of one-factor-at-a-time (OFAT) designs, which are inefficient. It is easy, via, say model.matrix() to write a general function to produce these. But I think it's a bad idea; more efiicient algorithmic designs are better, IMO, which is why I suggested AlgDesign. You and others are free to disagree, of course. Hi Bert, thanks for your suggestion. However, let us say that i need a 2x2x2x3x3x3 design, which should not be too hard. I've loaded AlgDesign, and i am aware now that gen.factorial allows me to create a full desing. But how to create a main-effects-only factorial design (orthogonal)? I am still not able to produce what i need. The function model.matrix.formula is not very clear... :( Could you please indicate which syntax should i use? I'd really appreciate your help. Thanks in advance, Roberto Furlan University of Turin, Italy La mia Cartella di Posta in Arrivo è protetta con SPAMfighter 188 messaggi contenenti spam sono stati bloccati con successo. Scarica gratuitamente SPAMfighter! __ 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
Re: [R] R: fractional factorial design in R
I think that there is an understandable wish to have the simple orthogonal plans (and be it only for non-experts to be able to analyse the results themselves). For mixed levels, there is e.g. the L36 that should be able to accomodate plans like 2x2x2x3x3x3. Unfortunately, R is not very strong in this arena. If I had more time, I would think about writing a package on comfortably designing experiments supported e.g. by the catalogues of Chen, J., Sun, D.X., and Wu, C.F.J. (1993). (A catalogue of two-level and three-level fractional factorial designs with small runs. International Statistical Review 61, 131-145.) Such a package should also provide the analysis facilities for any design generated with it, once it has been enriched with observed data. (This is a bit different from the typical R spirit, where users are often required to be experts themselves.) If anyone is planning a project like this or wants to make a diploma student work on it I would be interested in contributing. For the moment, if you want to implement main effects plans of the orthogonal sort (e.g. a Taguchi-plan like the L36) you have to use books or tables published on the internet, if you don't want to use expensive software like SPSS - not very comfortable, but possible. For example, you can find the L36 - which would be able to accomodate your 2x2x2x3x3x3 - in http://www.itl.nist.gov/div898/handbook/pri/section3/pri33a.htm. With kind regards, Ulrike In general, a main effects design need not be orthogonal -- the main effects merely need to be estimable. The trick is to estimate them with good efficiency, etc. I think you need to consult a local statistician for help to understand what these statistical concepts mean. In your example you could cross the 2^(3-1) with the 3^(3-1) to produce an orthogonal design to estimate main effects. But of course that's 72 runs, which I don't think you would consider small. As a previous poster commented, there are orthogonal mixed level arrays (Addleman, Kempthorne Youden -designs are a couple of phrases to try googling on) which stem from the 1960's. I doubt that, in general, they would satisfy your needs. I have not used the AlgDesign package myself. I suggest you direct questions about it to the author/maintainer, Bob Wheeler. -- Bert Gunter Genentech Non-Clinical Statistics South San Francisco, CA The business of the statistician is to catalyze the scientific learning process. - George E. P. Box -Original Message- From: r-help-bounces at stat.math.ethz.ch [mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of statistical.model at googlemail.com Sent: Monday, January 23, 2006 12:20 PM To: Berton Gunter; statistical.model at googlemail.com; r-help at stat.math.ethz.ch Subject: [R] R: fractional factorial design in R Yes, you're right. For, say, a 3 x 5 design, one can do this in as few as 7 runs -- but only in general by some version of one-factor-at-a-time (OFAT) designs, which are inefficient. It is easy, via, say model.matrix() to write a general function to produce these. But I think it's a bad idea; more efiicient algorithmic designs are better, IMO, which is why I suggested AlgDesign. You and others are free to disagree, of course. Hi Bert, thanks for your suggestion. However, let us say that i need a 2x2x2x3x3x3 design, which should not be too hard. I've loaded AlgDesign, and i am aware now that gen.factorial allows me to create a full desing. But how to create a main-effects-only factorial design (orthogonal)? I am still not able to produce what i need. The function model.matrix.formula is not very clear... :( Could you please indicate which syntax should i use? I'd really appreciate your help. Thanks in advance, Roberto Furlan University of Turin, Italy La mia Cartella di Posta in Arrivo è protetta con SPAMfighter 188 messaggi contenenti spam sono stati bloccati con successo. Scarica gratuitamente SPAMfighter! __ 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
[R] weighted likelihood for lme
Dear R users,
I'm trying to fit a simple random intercept model with a fixed intercept.
Suppose I want to assign a weight w_i to the i-th contribute to the
log-likelihood, i.e.
w_i * logLik_i
where logLik_i is the log-likelihood for the i-th subject.
I want to maximize the likelihood for N subjects
Sum_i {w_i * logLik_i}
Here is a simple example to reproduce
# require(nlme)
foo - Orthodont
lme(distance ~ 1, random = ~ 1|Subject, method=ML, data = foo)
Linear mixed-effects model fit by maximum likelihood
Data: foo
Log-likelihood: -257.7456
Fixed: distance ~ 1
(Intercept)
24.02315
Random effects:
Formula: ~1 | Subject
(Intercept) Residual
StdDev:1.888748 2.220312
Number of Observations: 108
Number of Groups: 27
Then I assign arbitrary weights, constant within the group. I want to give
weight 1 to the first 5 subjects, and weight 0.5 to the others 22 (4 is the
number of repeated measurements for each subject)
foo$w - c(rep(1, 5*4), rep(0.5, 22*4))
Maybe I am missing something, but I believe that
lme(distance ~ 1, random = ~ 1|Subject, method=ML, data = foo, weight=~w)
does not maximize the likelihood Sum_i {w_i * logLik_i}, since 'weight'
describes the with-in heteroscedasticity structure.
I think I need something like the option 'iweight' (importance weight) for
the command 'xtreg' of Stata.
Any suggestion for R?
Thanks in advance,
Marco Geraci
sessionInfo()
R version 2.2.1, 2005-12-20, i386-pc-mingw32
attached base packages:
[1] methods stats graphics grDevices utils
[6] datasets base
other attached packages:
nlme
3.1-66
-
What are the most popular cars? Find out at Yahoo! Autos
[[alternative HTML version deleted]]
__
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
Re: [R] Easy, Robust and Stable GUI???
On Mon, 23 Jan 2006 12:44:49 -0800 (PST) pat_primate (sent by Nabble.com) wrote: I know that this isn't really a R help question, but I am a psychology student at TRU (tru.ca) and my psych department is going to be switching statistical software in the near future. I thought this might be a good oppertunity to advocate for open source if an acceptable option is available. I have looked around a bit and R seems to be the most stable and mature (not to mention powerful) open source statistical program going. The only downfall is that the school has been using spss for years and would demand a similarly user friendly GUI based statistical program to replace it. I have looked at a few of the R guis and most of them look like they are just command line interfaces in pretty desktop windows and not really a gui like spss. If anyone knows of any stable, userfriendly and robust guis for R that would be similar to using spss please let me know, as I would love for my school to start embracing open source software. Have you looked at John Fox's Rcmdr package? See http://socserv.mcmaster.ca/jfox/Misc/Rcmdr/ and John Fox (2005). The R Commander: A Basic-Statistics Graphical User Interface to R, Journal of Statistical Software, 14(9). URL http://www.jstatsoft.org/ Also look at http://www.sciviews.org/_rgui/ for an overview of other GUI projects. Best, Z Thanks Pat -- View this message in context: http://www.nabble.com/Easy%2C-Robust-and-Stable-GUI--t982193.html#a2543480 Sent from the R help forum at Nabble.com. [[alternative HTML version deleted]] __ 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 __ 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
Re: [R] Latest revision of lme4 requires 'Matrix' = 0.995.2 but that version is not available on CRAN
John Logsdon [EMAIL PROTECTED] writes: Doug and list No, the change as reported on my XP PC was Matrix package 0.995-1 was found but lme4 requires = 0.995.2. The format change was from a dash to a dot. As far as I remember, the version comparison logic is separator-agnostic, so it's purely a cosmetic issue. Maybe a few more would spell SOS! Some of the users are already going ... --- ... / . .-.. .--. -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ 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
Re: [R] In which application areas is R used?
You could probably add: - Fisheries modelling - Oceanography Although there is still resistance of other software there, R is gaining more and more users in these fields. Best, Philippe Grosjean P.S.: if you need actual examples, just ask... ;-) John Maindonald wrote: If anyone has a list of application areas where there is extensive use of R, I'd like to hear of it. My current short list is: Bioinformatics Epidemiology Geophysics Agriculture and crop science John Maindonald Mathematical Sciences Institute, Australian National University. [EMAIL PROTECTED] __ 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 __ 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
[R] varphi symbol for ylab expression
Hi all, it is possible to invoke certain graphical functions (e.g. curve) with an expression argument, e.g. ylab=expression(phi). There are some greek letters with a second script. For instance, in latex two symbols do exist: phi and varphi. Is the second symbol also available in an expression()? If yes, how? Kind regards, Kilian __ 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
Re: [R] In which application areas is R used?
If it hasn't been mentioned yet, and if you want to consider this as a separate discipline from the ones mentioned below, we also use it for simulation modeling and risk analysis. Francisco From: John Maindonald [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Subject: [R] In which application areas is R used? Date: Tue, 24 Jan 2006 06:35:00 +1100 (EST) If anyone has a list of application areas where there is extensive use of R, I'd like to hear of it. My current short list is: Bioinformatics Epidemiology Geophysics Agriculture and crop science John Maindonald Mathematical Sciences Institute, Australian National University. [EMAIL PROTECTED] __ 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 __ 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
Re: [R] Easy, Robust and Stable GUI???
Yes, Rcmdr is certainly the closest match. Note, however, that there are good reasons not to replicate SPSS style of GUI. This is because driving an analysis using scripts has three major advantages: - flexibility: a good, high-level programming language allows to do much more than even the best GUI. This is because, as soon as you have programmed a dialog box, you restrict possibilities to the couple of choices that you hardcoded in that dialog box. With R, the only limit is your imagination (if something does not exist, you can program it by yourself). - traceability: with a GUI, how do you remember all the mouse clicks that led you to a given analysis? On the contrary, a script is an accurate record of all steps. - comprehension: to construct a R script, you must understand the analysis. R forces to learn the logic behind *before* you can run that analysis. With a menu/dialog box interface, you can click everywhere and get results by chance. Statistical packages with intuitive GUIs tend to stimulate lazyness: here, come! Look like I am a sexy GUI! Look, I am sooo easy to use! And I can deliver you plenty of results, ... No, no, don't be afraid, you don't need to understand what you're doing. Just click me!. So, all GUIs proposed for R are just ways to learn in an easier way how to write R scripts. Even R Commander tries hard to stimulate use of R scripts... and you should consider a lack of a good GUI for R as a sign of quality and nothing else. Best, Philippe Grosjean Achim Zeileis wrote: On Mon, 23 Jan 2006 12:44:49 -0800 (PST) pat_primate (sent by Nabble.com) wrote: I know that this isn't really a R help question, but I am a psychology student at TRU (tru.ca) and my psych department is going to be switching statistical software in the near future. I thought this might be a good oppertunity to advocate for open source if an acceptable option is available. I have looked around a bit and R seems to be the most stable and mature (not to mention powerful) open source statistical program going. The only downfall is that the school has been using spss for years and would demand a similarly user friendly GUI based statistical program to replace it. I have looked at a few of the R guis and most of them look like they are just command line interfaces in pretty desktop windows and not really a gui like spss. If anyone knows of any stable, userfriendly and robust guis for R that would be similar to using spss please let me know, as I would love for my school to start embracing open source software. Have you looked at John Fox's Rcmdr package? See http://socserv.mcmaster.ca/jfox/Misc/Rcmdr/ and John Fox (2005). The R Commander: A Basic-Statistics Graphical User Interface to R, Journal of Statistical Software, 14(9). URL http://www.jstatsoft.org/ Also look at http://www.sciviews.org/_rgui/ for an overview of other GUI projects. Best, Z Thanks Pat -- View this message in context: http://www.nabble.com/Easy%2C-Robust-and-Stable-GUI--t982193.html#a2543480 Sent from the R help forum at Nabble.com. [[alternative HTML version deleted]] __ 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 __ 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 __ 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
Re: [R] In which application areas is R used?
Please don't forget engineering! (e.g. fatigue and reliability - censored regression and survival; quantitative nondestructive evaluation - GLM) Charles Annis, P.E. [EMAIL PROTECTED] phone: 561-352-9699 eFax: 614-455-3265 http://www.StatisticalEngineering.com -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of John Maindonald Sent: Monday, January 23, 2006 2:35 PM To: r-help@stat.math.ethz.ch Subject: [R] In which application areas is R used? If anyone has a list of application areas where there is extensive use of R, I'd like to hear of it. My current short list is: Bioinformatics Epidemiology Geophysics Agriculture and crop science John Maindonald Mathematical Sciences Institute, Australian National University. [EMAIL PROTECTED] __ 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 __ 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
Re: [R] In which application areas is R used?
Define extensive. I think your answers depend on your definition. I know a bunch of folks in pharmaceutical preclinical RD who use R for all sorts of stuff (analysis and visualization of tox and efficacy animal studies, dose/response modeling, PK work, IC50 determination, stability data analysis, etc.). Is bunch a majority? I strongly doubt that it's near. Is it 5%, 10%, 30% ?? Dunno. Excel is still the Big Boy in most of these arenas I would bet. But I would also bet that there are at least 1 or 2 folks in dozens of companies who use R in for these things. Is there a subtext to your query? -- i.e. are you trying to make an argument for something? -- Bert -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of John Maindonald Sent: Monday, January 23, 2006 11:35 AM To: r-help@stat.math.ethz.ch Subject: [R] In which application areas is R used? If anyone has a list of application areas where there is extensive use of R, I'd like to hear of it. My current short list is: Bioinformatics Epidemiology Geophysics Agriculture and crop science John Maindonald Mathematical Sciences Institute, Australian National University. [EMAIL PROTECTED] __ 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 __ 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
[R] (no subject)
Dear list members, I have to apologize. I overlooked a remark in the docs of mathplot. My problem is resolved. Kind regards, Kilian __ 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
Re: [R] In which application areas is R used?
my favorites: customer/marketing analytics -- HTH, Jim Porzak Loyalty Matrix Inc. San Francisco, CA [[alternative HTML version deleted]] __ 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
[R] exporting dates into Microsoft SQL Server
I am running R 2.1.1 in a Windows XP environment. I wish to use the sqlSave command to export a dataframe into Microsoft SQL. My dataframe is called temp and has 2 columns, monthenddate and value. Monthenddate is in 'POSIXct', format. (i.e. 'POSIXct', format: chr 1984-01-31 1984-01-31 1984-01-31 1984-01-31 ...). How can I export this dataframe into SQL and have the format in SQL by one of the standard SQL date formats? I am using the following r code: db - odbcConnect(testserver) sqlSave(db, temp) __ 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
Re: [R] command in survival package
On Mon, 2006-01-23 at 10:52 -0800, Thomas Lumley wrote: On Mon, 23 Jan 2006, Linda Lei wrote: Thank you guys. But I tried the commands and I still get: aml1-aml[aml$group==1,] aml1 [1] time status x 0 rows (or 0-length row.names) esf.fit - survfit(Surv(aml1$weeks,status) ~ 1) Error in Surv(aml1$weeks, status) : Time variable is not numeric In addition: Warning message: is.na() applied to non-(list or vector) in: is.na(time) which still looks confusing. Or are they should be applied in s-plus instead of R? You *still* haven't said where the aml dataset comes from, but as I said before, it isn't the same as the one built in to R, so you need to load it somehow. The one in R has columns called time, status and x; you appear to want one with columns weeks,status, and group, and with group being numeric rather than factor. -thomas I don't have the book with me (it's at home), but I suspect that the problem here is that the 'aml' dataset provided at the aforementioned web site: http://www.crcpress.com/e_products/downloads/download.asp?cat_no=C4088 which is to be used with the code under discussion, was more than likely not imported into an R session by Linda. Since one needs to do a: library(survival) to utilize the R code examples, that loads that package's 'aml' dataset, resulting in: aml[aml$group==1,] [1] time status x 0 rows (or 0-length row.names) since there is no 'group' column in the built in 'aml' dataset as Thomas points out. There is such a structure to the authors' version of the dataset: str(read.table(aml.txt, header = TRUE)) `data.frame': 23 obs. of 3 variables: $ weeks : num 9 13 13 18 23 28 31 34 45 48 ... $ group : num 1 1 1 1 1 1 1 1 1 1 ... $ status: num 1 1 0 1 1 0 1 1 0 1 ... Thus: aml - read.table(aml.txt, header = TRUE) (aml1 - aml[aml$group==1,]) weeks group status 1 9 1 1 2 13 1 1 3 13 1 0 4 18 1 1 5 23 1 1 6 28 1 0 7 31 1 1 8 34 1 1 9 45 1 0 1048 1 1 11 161 1 0 This bring us to the still remaining error in the authors' survival code, which is not fully corrected in the authors' online errata: esf.fit - survfit(Surv(aml1$weeks,status) ~ 1) Error in Surv(aml1$weeks, status) : object status not found Thus, something like one of the following should be used instead: esf.fit - survfit(Surv(aml1$weeks, aml1$status) ~ 1) esf.fit - with(aml1, survfit(Surv(weeks, status) ~ 1)) Hi all, A quick follow up here. Prof. Kim, one of the authors for the book in question, replied to my e-mail of earlier today. There are two issues here: 1. The confounding of the two versions of the 'aml' data set, which has been identified above. Linda needs to be sure to import the authors' version of the data set to be able to follow along with the code examples and exercises in the book. 2. In the code that Linda posted above, in combination with my not having the book at hand earlier today, there is a single critical line of code missing that impacts my reply with respect to the final couple of statements. The three full lines of code should be: aml1 - aml[aml$group==1,] status - rep(1, 11) esf.fit - survfit(Surv(aml1$weeks,status) ~ 1) The middle line, creating the local vector 'status', is why the code that appears corrected in the errata does in fact work and why my corrections above are not required. Hope those clarifications help. Marc Schwartz __ 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
Re: [R] In which application areas is R used?
In this context extensive might be use of R in at least maybe 2% or 5% of the published analyses in the area, enough to make waves and stir awareness. The immediate subtext is the demand of a book publisher for a list of journals to which a new edition of a certain book might be sent for review, and for a list of conferences where it might be given exposure. For myself, in the medium to longer term, I am more interested in other subtexts such as you mention, to which the answer might have relevance. I've wondered what support there'd be for starting a database of bibliographic information on papers where R was used for the analysis. Authors might supply the information, or readers of a paper suggest its addition to the database. Once well populated, this would provide a useful indication of the range of application areas and journals where R is finding use. [Or has someone, somewhere, already started such a database?] Finance and biostatistics are obvious areas that I'd omitted. Other areas drawn to my attention have been telephony and electronic networks, solid state etc manufacturing, computer system performance, oceanography and fisheries research, risk analysis, process engineering and marketing. (I hope my summaries are acceptably accurate). I'm not sure what force these other respondents have given the word extensive. John Maindonald Mathematical Sciences Institute Australian National University. [EMAIL PROTECTED] Berton Gunter wrote: Define extensive. I think your answers depend on your definition. I know a bunch of folks in pharmaceutical preclinical RD who use R for all sorts of stuff (analysis and visualization of tox and efficacy animal studies, dose/response modeling, PK work, IC50 determination, stability data analysis, etc.). Is bunch a majority? I strongly doubt that it's near. Is it 5%, 10%, 30% ?? Dunno. Excel is still the Big Boy in most of these arenas I would bet. But I would also bet that there are at least 1 or 2 folks in dozens of companies who use R in for these things. Is there a subtext to your query? -- i.e. are you trying to make an argument for something? -- Bert -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] __ 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
Re: [R] In which application areas is R used?
Might it be reasonable to connect this with the recent thread on a possible R Wiki? (See, e.g., www.sciviews.org/_rgui/wiki/doku.php.) Am I correct that anyone can add an entry to a Wikipedia? If yes, we just need to invite people with manuscripts and publications using R to post an entry. What do you think? spencer graves John Maindonald wrote: In this context extensive might be use of R in at least maybe 2% or 5% of the published analyses in the area, enough to make waves and stir awareness. The immediate subtext is the demand of a book publisher for a list of journals to which a new edition of a certain book might be sent for review, and for a list of conferences where it might be given exposure. For myself, in the medium to longer term, I am more interested in other subtexts such as you mention, to which the answer might have relevance. I've wondered what support there'd be for starting a database of bibliographic information on papers where R was used for the analysis. Authors might supply the information, or readers of a paper suggest its addition to the database. Once well populated, this would provide a useful indication of the range of application areas and journals where R is finding use. [Or has someone, somewhere, already started such a database?] Finance and biostatistics are obvious areas that I'd omitted. Other areas drawn to my attention have been telephony and electronic networks, solid state etc manufacturing, computer system performance, oceanography and fisheries research, risk analysis, process engineering and marketing. (I hope my summaries are acceptably accurate). I'm not sure what force these other respondents have given the word extensive. John Maindonald Mathematical Sciences Institute Australian National University. [EMAIL PROTECTED] Berton Gunter wrote: Define extensive. I think your answers depend on your definition. I know a bunch of folks in pharmaceutical preclinical RD who use R for all sorts of stuff (analysis and visualization of tox and efficacy animal studies, dose/response modeling, PK work, IC50 determination, stability data analysis, etc.). Is bunch a majority? I strongly doubt that it's near. Is it 5%, 10%, 30% ?? Dunno. Excel is still the Big Boy in most of these arenas I would bet. But I would also bet that there are at least 1 or 2 folks in dozens of companies who use R in for these things. Is there a subtext to your query? -- i.e. are you trying to make an argument for something? -- Bert -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] __ 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 __ 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
Re: [R] R: fractional factorial design in R
If an orthogonal main effect plan exists for the number of trials you specify, optFederov() in AlgDesign will more than likely find it for you, since such a design should be an optimal design. Ulrike Grömping wrote: I think that there is an understandable wish to have the simple orthogonal plans (and be it only for non-experts to be able to analyse the results themselves). For mixed levels, there is e.g. the L36 that should be able to accomodate plans like 2x2x2x3x3x3. Unfortunately, R is not very strong in this arena. If I had more time, I would think about writing a package on comfortably designing experiments supported e.g. by the catalogues of Chen, J., Sun, D.X., and Wu, C.F.J. (1993). (A catalogue of two-level and three-level fractional factorial designs with small runs. International Statistical Review 61, 131-145.) Such a package should also provide the analysis facilities for any design generated with it, once it has been enriched with observed data. (This is a bit different from the typical R spirit, where users are often required to be experts themselves.) If anyone is planning a project like this or wants to make a diploma student work on it I would be interested in contributing. For the moment, if you want to implement main effects plans of the orthogonal sort (e.g. a Taguchi-plan like the L36) you have to use books or tables published on the internet, if you don't want to use expensive software like SPSS - not very comfortable, but possible. For example, you can find the L36 - which would be able to accomodate your 2x2x2x3x3x3 - in http://www.itl.nist.gov/div898/handbook/pri/section3/pri33a.htm. With kind regards, Ulrike In general, a main effects design need not be orthogonal -- the main effects merely need to be estimable. The trick is to estimate them with good efficiency, etc. I think you need to consult a local statistician for help to understand what these statistical concepts mean. In your example you could cross the 2^(3-1) with the 3^(3-1) to produce an orthogonal design to estimate main effects. But of course that's 72 runs, which I don't think you would consider small. As a previous poster commented, there are orthogonal mixed level arrays (Addleman, Kempthorne Youden -designs are a couple of phrases to try googling on) which stem from the 1960's. I doubt that, in general, they would satisfy your needs. I have not used the AlgDesign package myself. I suggest you direct questions about it to the author/maintainer, Bob Wheeler. -- Bert Gunter Genentech Non-Clinical Statistics South San Francisco, CA The business of the statistician is to catalyze the scientific learning process. - George E. P. Box -Original Message- From: r-help-bounces at stat.math.ethz.ch [mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of statistical.model at googlemail.com Sent: Monday, January 23, 2006 12:20 PM To: Berton Gunter; statistical.model at googlemail.com; r-help at stat.math.ethz.ch Subject: [R] R: fractional factorial design in R Yes, you're right. For, say, a 3 x 5 design, one can do this in as few as 7 runs -- but only in general by some version of one-factor-at-a-time (OFAT) designs, which are inefficient. It is easy, via, say model.matrix() to write a general function to produce these. But I think it's a bad idea; more efiicient algorithmic designs are better, IMO, which is why I suggested AlgDesign. You and others are free to disagree, of course. Hi Bert, thanks for your suggestion. However, let us say that i need a 2x2x2x3x3x3 design, which should not be too hard. I've loaded AlgDesign, and i am aware now that gen.factorial allows me to create a full desing. But how to create a main-effects-only factorial design (orthogonal)? I am still not able to produce what i need. The function model.matrix.formula is not very clear... :( Could you please indicate which syntax should i use? I'd really appreciate your help. Thanks in advance, Roberto Furlan University of Turin, Italy La mia Cartella di Posta in Arrivo è protetta con SPAMfighter 188 messaggi contenenti spam sono stati bloccati con successo. Scarica gratuitamente SPAMfighter! __ 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 -- Bob Wheeler --- http://www.bobwheeler.com/ ECHIP, Inc. --- Randomness comes in bunches. __ 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
[R] An Appreciation of Leo Breiman (1928-2005)
We are organizing three projects to honor Leo Breiman this year. First, Salford Systems' Data Mining Conference will open with a special session devoted to his scientific contributions. Second, we would like to construct Leo's scientific family tree, identifying Leo's students, collaborators, and others whose work has been influenced in an important way by Leo's research and professional activities. Finally, we would like to create a small memory book of appreciative notes and thoughts, stories, or photos which we will collate to present to Leo's family. Please send your contributions for the scientific genealogy or memory book to [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] Lesser known Gems in Breiman's Research: The opening session, from 7-9PM on March 29th, will feature a discussion of Leo Breiman's extensive contributions to data mining, machine learning, and statistics. The session will focus on some of Breiman's lesser known innovations that may be influential in the future. Speakers will include: - Richard Carson, University of California, San Diego - Adele Cutler, Utah State University - Jerome Friedman, Stanford University - Richard Olshen, Stanford University - Chuck Stone, University of California, Berkeley - Rob Tibshirani, Stanford University The Conference, which continues on March 30-31, will include many papers on CART(R), Bagging, RandomForests(tm), as well as MARS(R), TreeNet(tm), and other topics related to the more recent work of Jerome Friedman and Richard Olshen. Applied areas include credit risk, fraud detection, targeted marketing, actuarial risk, bioinformatics, medical informatics, quality control, and other scientific applications. For further information please email: [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] or call (619) 543-8880 Conference Website: http://www.salforddatamining.com [[alternative HTML version deleted]] __ 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
Re: [R] Converting from a dataset to a single column
Hi ?stack and ?unlist are good starting points. HTH Petr On 23 Jan 2006 at 9:49, r user wrote: Date sent: Mon, 23 Jan 2006 09:49:40 -0800 (PST) From: r user [EMAIL PROTECTED] To: rhelp r-help@stat.math.ethz.ch Subject:[R] Converting from a dataset to a single column I have a dataset of 3 columns and 5 rows . temp-data.frame(col1=c(5,10,14,56,7),col2=c(4,2,8,3,34),col3=c(28,4,5 2,34,67)) I wish to convert this to a single column , with column 1 on top and column 3 on bottom . i.e. 5 10 14 56 7 4 2 8 3 34 28 4 52 34 67 Are there any functions that do this, and that will work well on much larger datasets (e.g. 1000 rows, 6000 columns)? __ 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 Petr Pikal [EMAIL PROTECTED] __ 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
Re: [R] mutlivariate normal and t distributions
On Mon, 23 Jan 2006, Spencer Graves wrote: Thanks for this. I got stuck some months ago, because I needed to evaluate a certain special normal tail region in at least 10,000 dimensional space, and mvtnorm could not give me adequate numerical precision above about 30 or 35 dimensions. When I get time to return to that project, I will be particularly interested in looking at your code. I would strongly encourage you to submit your package to CRAN. yes, Adelchi, you should definitely submit the package to CRAN! Otherwise it will be harder for people to learn about it and get it. If your package contains functions or other objects with the same names as objects in other packages, that fact could create a conflict, though not insurmountable. If you can make some effort to minimize the potential for name conflicts with other packages, that would be great. However, even without that, I prefer accessibility. Of course, from a user's perspective, it would be best if you and the 'mvtnorm' maintainer (Torsten Hothorn) could develop a consensus on the circumstances under which each algorithm is best and then develop a combined package that makes it easier for users to access the best known method -- and to easily switch between methods, when it may not be clear which is best. However, if you and Torsten don't have time energy for that, I would still encourage you to submit your package to CRAN. we already talked about such ideas but, for the time being, having two packages should not be a big problem. Best, Torsten Best Wishes, Spencer Graves Adelchi Azzalini wrote: Dear R-help list members, I have created a package 'mnormt' with facilities for the multivariate normal and t distributions. The core part is simply an interface to Fortran routines by Alan Genz for computing the integral of two densities over rectangular regions, using an adaptive integration method. Other R functions compute densities and generate random numbers. The starting motivation to write it was the need to have functions which compute the distribution functions in a non-Monte Carlo form, sinse this caused me problems when these probabilities are involved in a minimization problem. For this reason, I could not make use of the CRAN package 'mvtnorm'. Exactly to avoid superposition with the CRAN package, 'mnormt' is made available somehere else, in case other people want to use it. The package 'mnormt' is at http://azzalini.stat.unipd.it/SN/Pkg-mnormt As explained, this is not uploaded to CRAN just to avoid clash with the existing package. However, if it is felt appropriate, I have no objection to upload it to CRAN. Best wishes, Adelchi Azzalini __ 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
