[R] Workshop on Statistics in Functional Genomics 2004
Apologies in advance if you receive multiple copies of this email. This is to announce and invite your participation in a workshop on Statistics in Functional Genomics, to be held from 27 June - 2 July 2004 at Ascona in the Italian-speaking part of Switzerland. The purpose of the workshop is to bring together participants from statistics, computational sciences, bioinformatics and biology, and aim to encourage interaction among them. Confirmed invited speakers include: Philip Brown (Kent), Sandrine Dudoit (Berkeley), Robert Gentleman (Harvard), Othmar Pfannes (GeneData), Sylvia Richardson (Imperial College), Terry Speed (Berkeley), Martin Vingron (Max Planck Institute), Anja Wille (ETH Zurich). Other acceptances are pending. Contributed presentations will also be welcome. More details and pre-registration instructions are available at http://www.stat.math.ethz.ch/talks/Ascona_04 Peter Bühlmann Anthony Davison Darlene Goldstein Eidgenoessische Technische Hochschule Zuerich Swiss Federal Institute of Technology Zurich Christina Kuenzli[EMAIL PROTECTED] Seminar fuer Statistik Leonhardstr. 27, LEO D11 phone: +41 1 632 3438 ETH Zentrum, fax : +41 1 632 1228 CH-8092 Zurich, Switzerlandhttp://stat.ethz.ch/ __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] would like to know how to simulated a GARCH(1,2)
Follow the example in tseries, we can simulated a GARCH(0,2),
n - 1100
a - c(0.1, 0.5, 0.2) # ARCH(2) coefficients
e - rnorm(n)
x - double(n)
x[1:2] - rnorm(2, sd = sqrt(a[1]/(1.0-a[2]-a[3])))
for(i in 3:n) # Generate ARCH(2) process
{
x[i] - e[i]*sqrt(a[1]+a[2]*x[i-1]^2+a[3]*x[i-2]^2)
}
x - ts(x[101:1100])
and x is a GARCH(0,2).
But, I would like to know how to simulated a GARCH(1,2) ?
[[alternative HTML version deleted]]
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
RE: [R] multiple peaks in data frame
Hello! why not try the R site search for peaks: http://finzi.psych.upenn.edu/search.html which gives you (among other things): http://finzi.psych.upenn.edu/R/Rhelp02a/archive/7593.html Hope this helps, J. Joerg Rieckermann Environmental Engineering Swiss Federal Institute for Environmental Science and Technology (EAWAG) -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Sent: Mittwoch, 26. November 2003 23:09 To: [EMAIL PROTECTED] Subject: [R] multiple peaks in data frame Hello, it wanted to know how I can extract of a dates frame the values peaks according to an interval that I establish. For example if dates are: 1 23 2 4 3 56 4 7 5 99 6 33 extract the date i wanted to divide into intervals of 2 an d to take alone the numbers 23, 56 and 99 of those 3 intervals. Thanks Ruben __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo /r-help __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] would like to know how to simulated a GARCH(1,2)
Prelude for those not in the know:
GARCH models the variance of a times series
conditional on past information (often only the
series itself). It is a reasonably good model of
the variance of the returns of market-priced
assets, which display big jumps upwards in
variance followed by gradual decays.
Rob Engle is just about to receive the Nobel Prize
in Economics for originating the model (without
the G for generalized).
The Answer:
You need to create a vector of conditional variances,
traditionally called h. So at the start you will have an
extra line:
h - double(n)
in the for loop you will have:
h[i] - a[1]+a[2]*x[i-1]^2+a[3]*x[i-2]^2 + b[1] * h[i-1]
x[i] - e[i] * sqrt(h[i])
This leaves just one (I think) detail:
What is the initial value of h? This will depend on what you
are doing. If you are simulating into the future, then you
want to use the (conditional) variance for the present.
Other choices can be the observed unconditional variance
and a random selection from the estimated conditional
variances that are observed.
Patrick Burns
Burns Statistics
[EMAIL PROTECTED]
+44 (0)20 8525 0696
http://www.burns-stat.com
(home of S Poetry and A Guide for the Unwilling S User)
M. M. Palhoto N. Rodrigues wrote:
Follow the example in tseries, we can simulated a GARCH(0,2),
n - 1100
a - c(0.1, 0.5, 0.2) # ARCH(2) coefficients
e - rnorm(n)
x - double(n)
x[1:2] - rnorm(2, sd = sqrt(a[1]/(1.0-a[2]-a[3])))
for(i in 3:n) # Generate ARCH(2) process
{
x[i] - e[i]*sqrt(a[1]+a[2]*x[i-1]^2+a[3]*x[i-2]^2)
}
x - ts(x[101:1100])
and x is a GARCH(0,2).
But, I would like to know how to simulated a GARCH(1,2) ?
[[alternative HTML version deleted]]
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] FDA and ICH Compliance of R
Have you tried www.r-project.org - search - R site search?
This issue has been discussed in the past. With luck, you may find
something there that might help.
hope this helps. spencer graves
Antonia Drugica wrote:
I'm quite new to this medical stuff. But my associates told me that we are
not free in choice of Statistical Software because the FDA has high
standards concerning this topic. But if they would prefer a specific
package (like SAS) that could mean, that this package vendourer could lay
back and hold it's hand open for licence money.
Is there any part of the ICH document referring to software packages? I
really would use R for some tasks but therefor I need arguments...
Antonia Drugica [EMAIL PROTECTED] writes:
Does anybody know if R is FDA or ICH (or EMEA...) compliant? AFAIK
S-Plus
is but that means nothing...
As Thomas pointed out, that does mean nothing -- there was a group of
folks discussing what might be done to help, earlier this year, but
then everyone got busy...
best,
-tony
--
[EMAIL PROTECTED]http://www.analytics.washington.edu/
Biomedical and Health Informatics University of Washington
Biostatistics, SCHARP/HVTN Fred Hutchinson Cancer Research Center
UW (Tu/Th/F): 206-616-7630 FAX=206-543-3461 | Voicemail is unreliable
FHCRC (M/W): 206-667-7025 FAX=206-667-4812 | use Email
CONFIDENTIALITY NOTICE: This e-mail message and any attachme...{{dropped}}
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
--
Trebate bolji pristup internetu?
Nazovite IskonInternet na 0800 1000 ili pogledajte
http://www.iskon.biz/individualni/usluge/dialup/
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] OT: apt-get and R in Debian
Hi everybody, Sorry for the OffTopic, but I always have a problem using apt-get to update my debian siystem and R. Anytime it updates the packages (right now I installed a self-compiled version of 1.8.1), even if they are exactly the same. Anybody can help me? TIA, Stefano __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
RE: RE: [R] Correlation test in time series
Thanks for you help, And how to test covariance = zero in time series , cov(r_t, r_t-1)=0 and r_t are homoscedastik and dependent ? How about: ?acf ?pacf in package 'ts' Box.test from package 'ts' best Adrian -- Dr. Adrian Trapletti Trapletti Statistical Computing Wildsbergstrasse 31, 8610 Uster Switzerland Phone Fax : +41 (0) 1 994 5631 Mobile : +41 (0) 76 370 5631 Email : mailto:[EMAIL PROTECTED] WWW : http://trapletti.homelinux.com __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] Blocked Mail Notification
[EMAIL PROTECTED] writes: * eManager Notification ** Recipient, Content filter has detected a sensitive e-mail. Source mailbox: [EMAIL PROTECTED] Destination mailbox(es): [EMAIL PROTECTED] *** End of message *** Received: from 129.73.8.34 by postoffice.scr.siemens.com (InterScan E-Mail VirusWall NT); Thu, 27 Nov 2003 06:12:27 -0500 Received: from idmz1.scr.siemens.com ([129.73.8.9]) by scr.siemens.com (8.11.7/8.11.7) with ESMTP id hARBCMg06444 for [EMAIL PROTECTED]; Thu, 27 Nov 2003 06:12:22 -0500 (EST) X-SCR-Return-Path: [EMAIL PROTECTED] (as seen by idmz1.scr.siemens.com) Received: from hypatia.math.ethz.ch (hypatia.ethz.ch [129.132.58.23]) by idmz1.scr.siemens.com (8.12.10/8.12.10) with ESMTP id hARBCTmN022366 for [EMAIL PROTECTED]; Thu, 27 Nov 2003 06:12:30 -0500 (EST) Received: from hypatia.math.ethz.ch (hypatia [129.132.58.23]) by hypatia.math.ethz.ch (8.12.10/8.12.10) with ESMTP id hARB53Cw016647; Thu, 27 Nov 2003 12:09:26 +0100 (MET) Date: Thu, 27 Nov 2003 12:09:26 +0100 (MET) Message-Id: [EMAIL PROTECTED] From: [EMAIL PROTECTED] Subject: R-help Digest, Vol 9, Issue 27 To: [EMAIL PROTECTED] Reply-To: [EMAIL PROTECTED] MIME-Version: 1.0 [ and proceeds to spew the entire digest message into r-help!] Will someone please tell these guys how to configure their MTA correctly (errors should *never* go to the Reply-To field), and/or unsubscribe mr. [EMAIL PROTECTED] Grrr -- O__ Peter Dalgaard Blegdamsvej 3 c/ /'_ --- Dept. of Biostatistics 2200 Cph. N (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] lagsarlm - using mixed explanatory variables (spdep package)
Hello I'm very new to R (which is excellent), so apologies if this has already been raised. In the spdep package, I'm trying to undertake an autoregressive mixed model using the lagsarlm function. This is working fine, but there does not appear to be a method of including an explanatory variable without it automatically being included as a lagged term. I'm after something along the lines of y = rho.W.y + x1 + x2 + lag(x2) but am only able to output y = rho.W.y + x1 + x2 + lag(x1) + lag(x2) Is there any way around this issue? Many thanks Roy Roy Sanderson Centre for Life Sciences Modelling Porter Building University of Newcastle Newcastle upon Tyne NE1 7RU United Kingdom Tel: +44 191 222 7789 [EMAIL PROTECTED] http://www.ncl.ac.uk/clsm __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] would like to know how to simulated a GARCH(1,2)
Follow the example in tseries, we can simulated a GARCH(0,2),
n - 1100
a - c(0.1, 0.5, 0.2) # ARCH(2) coefficients
e - rnorm(n)
x - double(n)
x[1:2] - rnorm(2, sd = sqrt(a[1]/(1.0-a[2]-a[3])))
for(i in 3:n) # Generate ARCH(2) process
{
x[i] - e[i]*sqrt(a[1]+a[2]*x[i-1]^2+a[3]*x[i-2]^2)
}
x - ts(x[101:1100])
and x is a GARCH(0,2).
But, I would like to know how to simulated a GARCH(1,2) ?
GARCH(1,1) something like
n - 1100
a - c(0.1, 0.2, 0.7)
e - rnorm(n)
x - double(n)
v - double(n)
v[1] - a[1]/(1.0-a[2]-a[3])
x[1] - rnorm(1, sd = sqrt(v[1]))
for(i in 2:n) {
v[i] - a[1]+a[2]*x[i-1]^2+a[3]*v[i-1]
x[i] - e[i]*sqrt(v[i])
}
x - ts(x[101:1100])
x.garch - garch(x, order = c(1,1))
summary(x.garch)
and accordingly the GARCH(1,2)
best
Adrian
--
Dr. Adrian Trapletti
Trapletti Statistical Computing
Wildsbergstrasse 31, 8610 Uster
Switzerland
Phone Fax : +41 (0) 1 994 5631
Mobile : +41 (0) 76 370 5631
Email : mailto:[EMAIL PROTECTED]
WWW : http://trapletti.homelinux.com
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] stl and NA
Hi, I try to figure out what the stl-function exactly do. I was reading the paper by Cleveland et al. (1990) and tested some features of stl (the ability to decompose time series with missing values and the robustness feature). I tried the following: data(co2) co2.na - co2 is.na(co2.na[c(50, 100)]) - TRUE plot(stl(co2.na, s.window = 12, na.action = na.exclude)) With the error message: Error in stl(co2.na, s.window = 12, na.action = na.exclude) : series is not periodic or has less than two periods The following works fine: plot(stl(co2, s.window = 12)) I had then a short look in the code of stl. Is it true that the argument na.action must be a generic function, one of ?na.fail? The help of stl: na.action action on missing values. (Mmmh, not really helpful) The other functions na.omit and na.pass do not what I was expecting?! plot(stl(co2.na, s.window = 12, na.action = na.omit)) Error in na.omit.ts(as.ts(x)) : time series contains internal NAs Is this feature correctly implemented? I do not found a bug report http://r-bugs.biostat.ku.dk/cgi-bin/R... So I assume that I'm missing something. How can I handle NAs in stl() correctly? Thanks for any hints and comments Thomas __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] OT: apt-get and R in Debian
On Thu, Nov 27, 2003 at 01:11:48PM +0100, Stefano Calza wrote: Sorry for the OffTopic, but I always have a problem using apt-get to update my debian siystem and R. Anytime it updates the packages (right now I installed a self-compiled version of 1.8.1), even if they are exactly the same. Anybody can help me? We probably need more info to help you. I presume you have CRAN and Debian testing in /etc/apt/sources.list? Did you try to use the apt configuration to give preference to one archive over another, or exclude one, or ... See some of the available apt documents, e.g. from the apt-howto package, should help. Also, 'apt-cache policy r-base-core' will tell how apt sees and ranks the archives you have set up. The easiest will probably be to simply exclude, say, CRAN. Dirk -- Those are my principles, and if you don't like them... well, I have others. -- Groucho Marx __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] FDA and ICH Compliance of R
On Thu, 27 Nov 2003, Antonia Drugica wrote: I'm quite new to this medical stuff. But my associates told me that we are not free in choice of Statistical Software because the FDA has high standards concerning this topic. But if they would prefer a specific package (like SAS) that could mean, that this package vendourer could lay back and hold it's hand open for licence money. Is there any part of the ICH document referring to software packages? I really would use R for some tasks but therefor I need arguments... As far as I can see, ICH has not said anything useful about software (the most relevant things are about data management). -thomas __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] FDA and ICH Compliance of R
On Thu, 27 Nov 2003 07:48:02 +0100 Antonia Drugica [EMAIL PROTECTED] wrote: I'm quite new to this medical stuff. But my associates told me that we are not free in choice of Statistical Software because the FDA has high standards concerning this topic. But if they would prefer a specific package (like SAS) that could mean, that this package vendourer could lay back and hold it's hand open for licence money. Your associates are completely wrong. It is only sponsors that choose not to be free in their choice, due in my humble opinion mainly to the fact that SAS has been in use since 1966 and that no one has ever been criticized by the FDA for using SAS. FDA even receives submissions based on Excel and we all know about the accuracy of Excel's statistical calculations. High standards need to be held by statisticians doing the analyses. Related to such standards open source systems such as R have many advantages, and the reproducible reporting capabilities of R using its Sweave package have major impacts on accuracy of reporting. I along with colleagues at another institution are working on an open source R package for clinical trial analysis and reporting that should be mature in about a year. I am currently using the package in two pharmaceutical industry-sponsored randomized clinical trials to report to data monitoring committees. I'm also working on a document addressing validation of statistical calculations. Let me know if you'd like a copy of the current version of that document. Is there any part of the ICH document referring to software packages? I really would use R for some tasks but therefor I need arguments... Don't know of anything in ICH. In view of the fact that large pharma companies have to pay more than $10M per year in SAS licenses and have to hire armies of non-intellectually challenged SAS programmers to do the work of significantly fewer programmers that use modern statistical computing tools like R and S-Plus, it is surprising that SAS is still the most commonly used tool in the clinical side of drug development. I quit using SAS in 1991 because my productivity jumped at least 20% within one month of using S-Plus. --- Frank E Harrell JrProfessor and ChairSchool of Medicine Department of BiostatisticsVanderbilt University __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] help me!
Would you help me to answer this question, please? /r/ is one of the most difficult English sounds to acquire and imitate. Describe in what ways it is different from our Spanish rolls (perro) and taps (pero). How does the pronunciation of this sound vary according to the context? Find at least three examples of linking r and intrusive r and transcribe into phonetics. When do we use them? Why are they used? I`ll waiting for your answer. Thanks Patricia [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] OT: apt-get and R in Debian
Can you give us more details, please? Which version of Debian (stable, testing or unstable) are you running and what are the relevant parts of your /etc/apt/sources.list file? (Just send us the whole file if you are not sure what parts are relevant.) Ok. Find attach my source.list + the output from apt-cache show r-base-core + apt-cache policy r-base-core. I use Debian/testing version + some unstable package. To others on the cc: list: May I suggest that we ask Martin to create an email list with a name like r-debian for Debian-specific questions about R installation? Yes, it would be a great idea! Thanks, Ste -- Douglas Bates[EMAIL PROTECTED] Statistics Department608/262-2598 University of Wisconsin - Madisonhttp://www.stat.wisc.edu/~bates/ -- Stefano Calza, Sezione di Statistica Medica Dip. di Scienze Biomediche e Biotecnologie Università degli Studi di Brescia - Italy Viale Europa, 11 25123 Brescia email: [EMAIL PROTECTED] Telefono/Phone: +390303717532 Fax: +390303701157 deb http://ftp.it.debian.org/debian/ stable main non-free contrib deb-src http://ftp.it.debian.org/debian/ stable main non-free contrib deb http://non-us.debian.org/debian-non-US stable/non-US main contrib non-free deb-src http://non-us.debian.org/debian-non-US stable/non-US main contrib non-free deb http://ftp.it.debian.org/debian/ testing main non-free contrib deb http://ftp.it.debian.org/debian-non-US testing/non-US main contrib non-free deb-src http://ftp.it.debian.org/debian testing main contrib non-free deb-src http://ftp.it.debian.org/debian-non-US testing/non-US main contrib non-free deb http://ftp.it.debian.org/debian/ unstable main non-free contrib deb http://ftp.it.debian.org/debian-non-US unstable/non-US main contrib non-free deb-src http://ftp.it.debian.org/debian unstable main contrib non-free deb-src http://ftp.it.debian.org/debian-non-US unstable/non-US main contrib non-free # R #deb http://cran.at.r-project.org/bin/linux/debian stable main #deb http://cran.at.r-project.org/bin/linux/debian testing main #deb http://cran.at.r-project.org/bin/linux/debian unstable main deb http://security.debian.org/ stable/updates main contrib non-free ## Java Environment #deb http://mirrors.publicshout.org/java-linux/debian testing main non-free #deb http://mirrors.publicshout.org/java-linux/debian unstable main non-free ## Bioconductor deb http://lab.analytics.washington.edu/debian-local ./ Package: r-base-core Priority: optional Section: math Installed-Size: 23916 Maintainer: Dirk Eddelbuettel [EMAIL PROTECTED] Architecture: i386 Source: r-base Version: 1.8.0.cvs.20031114-1 Replaces: r-base (= 1.4.1-1) Depends: perl, zlib-bin, libbz2-1.0, libc6 (= 2.3.2.ds1-4), libg2c0 (= 1:3.3.2-1), libgcc1 (= 1:3.3.2-1), libjpeg62, libncurses5 (= 5.3.20030510-1), libpcre3 (= 4.0), libpng10-0 (= 1.0.15-4), libreadline4 (= 4.3-1), tcl8.4 (= 8.4.2), tk8.4 (= 8.4.2), xlibs ( 4.1.0), zlib1g (= 1:1.1.4) Recommends: r-recommended, r-base-dev Suggests: libpaperg, ess, r-doc-info | r-doc-pdf | r-doc-html Filename: pool/main/r/r-base/r-base-core_1.8.0.cvs.20031114-1_i386.deb Size: 5939210 MD5sum: 8cc59556c1385f4ec50b84f69380c691 Description: GNU R core of statistical computing language and environment R is `GNU S' - A language and environment for statistical computing and graphics. R is similar to the award-winning S system, which was developed at Bell Laboratories by John Chambers et al. It provides a wide variety of statistical and graphical techniques (linear and nonlinear modelling, statistical tests, time series analysis, classification, clustering, ...). . R is designed as a true computer language with control-flow constructions for iteration and alternation, and it allows users to add additional functionality by defining new functions. For computationally intensive tasks, C, C++ and Fortran code can be linked and called at run time. . S is the statistician's Matlab and R is to S what Octave is to Matlab. . This package provides the core GNU R system from which only the optional documentation packages r-base-html, r-base-latex, r-doc-html, r-doc-pdf and r-doc-info have been split off to somewhat reduce the size of this package. Package: r-base-core Status: install ok installed Priority: optional Section: math Installed-Size: 23912 Maintainer: Dirk Eddelbuettel [EMAIL PROTECTED] Source: r-base Version: 1.8.0.cvs.20031114-1 Replaces: r-base (= 1.4.1-1) Depends: perl, zlib-bin, libbz2-1.0, libc6 (= 2.3.2.ds1-4), libg2c0 (= 1:3.3.2-1), libgcc1 (= 1:3.3.2-1), libjpeg62, libncurses5 (= 5.3.20030510-1), libpcre3 (= 4.0), libpng12-0 (= 1.2.5.0-4), libreadline4 (= 4.3-1), tcl8.4 (= 8.4.2), tk8.4 (= 8.4.2), xlibs ( 4.1.0), zlib1g (= 1:1.1.4) Recommends: r-recommended, r-base-dev Suggests: libpaperg, ess, r-doc-info | r-doc-pdf | r-doc-html Conffiles: /etc/R/Makeconf c819eaeb69d4f1514795e3a9eb7e2c9c /etc/R/Renviron
Re: [R] FDA and ICH Compliance of R
From: Frank E Harrell Jr [EMAIL PROTECTED] per year in SAS licenses and have to hire armies of non-intellectually challenged SAS programmers to do the work of significantly fewer programmers that use modern statistical computing tools like R and S-Plus, it is surprising that SAS is still the most commonly used tool in the clinical side of drug development. I quit using SAS in 1991 because my productivity jumped at least 20% within one month of using S-Plus. I have not used SAS for even longer than you but to give SAS its due: - its pretty easy to produce all the info you need for a complete analysis with a few SAS commands. It would be possible to create analogous R commands but as it stands you have to keep going back and forth with R rather than just get it all out at once like you can with SAS. - SAS has more functionality in missing values. You can have different types of SAS missing values but in R you can have only one type of missing value. - the BY phrase in SAS is incredibly powerful and handy. You can get the same effect in R but I think that specific functionality is easier with SAS. Obviously R is incredibly powerful and functional and I really am out of touch with the SAS world but I thought I would make whatever case I could. I am willing to be corrected by those more in the know with SAS if this wrong. __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] problems with R graph.
Hello, I have some problems to generate graph with R... I am working on two different platform : - Compaq Alpha Server (Unix True 64 5.1) + R 1.6 - Sparc Server (Sun Solaris 8) + R 1.6 I use different functions like the bitmap function, the legend function and the barplot function. The graph are made by the same script on the both platform. I obtain nice graph on the compaq server but the graph which is generate on the sun server has some problems... I don't understand why the result is not the same because we use the same library on each platform. Please look at these images to see what I mean. (See attached file: histogramme_bad.bmp)(See attached file: histogramme_good.bmp) thank you for your help. Aurelie.__ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] problems with R graph.
If indeed you used the bitmap() function, please read its help page. The differences are very likely due to the installations of ghostscript and nothing to do with R. There never was an `R 1.6', but the current version of R is 1.8.1, so it looks as if an update is well overdue. On Thu, 27 Nov 2003 [EMAIL PROTECTED] wrote: I have some problems to generate graph with R... I am working on two different platform : - Compaq Alpha Server (Unix True 64 5.1) + R 1.6 - Sparc Server (Sun Solaris 8) + R 1.6 I use different functions like the bitmap function, the legend function and the barplot function. The graph are made by the same script on the both platform. I obtain nice graph on the compaq server but the graph which is generate on the sun server has some problems... I don't understand why the result is not the same because we use the same library on each platform. Please look at these images to see what I mean. (See attached file: histogramme_bad.bmp)(See attached file: histogramme_good.bmp) You cannot send binary attachments to R-help, so we can't see anything here. In any case, .bmp is a strange choice for use on Unix systems: png would be much better for your readers here (but you would have to put them on a web site). -- 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 __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] significance in difference of proportions
Hello, I'm looking for some guidance with the following problem: I've 2 samples A (111 items) and B (10 items) drawn from the same unknown population. Witihn A I find 9 positives and in B 0 positives. I'd like to know if the 2 samples A and B are different, ie is there a way to find out whether the number of positives is significantly different in A and B? I'm currently using prop.test, but unfortunately some of my data contains less than 5 items in a group (like in the example above), and the test statistics may not hold: prop.test(c(9,0), c(111,10)) 2-sample test for equality of proportions with continuity correction data: c(9, 0) out of c(111, 10) X-squared = 0.0941, df = 1, p-value = 0.759 alternative hypothesis: two.sided 95 percent confidence interval: -0.02420252 0.18636468 sample estimates: prop 1 prop 2 0.08108108 0. Warning message: Chi-squared approximation may be incorrect in: prop.test(c(9, 0), c(111, 10)) Do you have suggestions for an alternative test? many thanks for your help, +kind regards, Arne __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
RE: [R] R 1.8.1 on SUSE 9.0
I think the problem is that by default g77 is not installed. However you should still be able to find the rpm on the CDROM. HTH, Andy Thanks to all for your replies. Indeed the package gcc-g77 was on the install disk, and I was able to install the R rpm with no problems. J.R. Lockwood 412-683-2300 x4941 [EMAIL PROTECTED] http://www.rand.org/methodology/stat/members/lockwood/ __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] lme v. aov?
I am trying to understand better an analysis mean RT in various conditions in a within subjects design with the overall mean RT / subject as one of the factors. LME seems to be the right way to do this. using something like m- lme(rt~ a *b *subjectRT, random= ~1|subject) and then anova(m,type = marginal). My understanding is that lme is an easy interface for dummy coding variables and doing a multiple regression (and that could be wrong). But, what is aov doing in this instance? MANOVA? I also haven't been able to find anything really useful on what to properly assign to random in the lme formula. For repeated measures the use above is always in the examples. __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] help me!
English may have greater variation between regional dialects than does Spanish, The Scots roll their r's, and I suspect it is more like the Spanish rolls (perro) than taps (pero), though I have not had enough contact with the Scots to judge. The English r may be closer to the r in Portuguese, French, and German than Spanish but does not close the throat. Try making an r like you do but without letting your tongue hit the roof of your mouth. hope this helps. Que esto pueda ayudarle! spencer graves Patricia wrote: Would you help me to answer this question, please? /r/ is one of the most difficult English sounds to acquire and imitate. Describe in what ways it is different from our Spanish rolls (perro) and taps (pero). How does the pronunciation of this sound vary according to the context? Find at least three examples of linking r and intrusive r and transcribe into phonetics. When do we use them? Why are they used? I`ll waiting for your answer. Thanks Patricia [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] lme v. aov?
Do you want to make inference about the specific subjects in your study? If yes, the subjects are a fixed effect. If instead you want to make inference about the societal processes that will generate the subjects you will get in the future, that is a random effect. The function lme handles both fixed and random effects, as does varcomp. The functions aov and lm are restricted to fixed effects only. You can use dummy coding for lm and aov as well. The the distinction between fixed and random effects seems to me to be the same as what Deming called the difference between enumerative and analytic studies: With a fixed effect / enumerative study, the objective is to determine the disposition of the sampling frame. For example, Deming managed a survey of food distribution in Japan in 1946 or so, right after World War II. The purpose was to determine where to deliver food the next day, etc., to keep people from dying of starvation. That was an enumerative study. If the purpose had been to advance economic theories for use not only in Japan or in 1946-47, that is an analytic study. Do you have the book Pinhiero and Bates (2000) Mixed-Effects Models in S and S-Plus (Springer)? If you have more than one use for analyzing data on human subjects, I suggest you get and study this book if you haven't already. Doug Bates and several of his graduate students have developed lme. I am not current in the absolute latest literature in that area of statistics, but Bates seems to me to be among the leaders in that area and specifically in statistical computing for that kind of problem. hope this helps. spencer graves John Christie wrote: I am trying to understand better an analysis mean RT in various conditions in a within subjects design with the overall mean RT / subject as one of the factors. LME seems to be the right way to do this. using something like m- lme(rt~ a *b *subjectRT, random= ~1|subject) and then anova(m,type = marginal). My understanding is that lme is an easy interface for dummy coding variables and doing a multiple regression (and that could be wrong). But, what is aov doing in this instance? MANOVA? I also haven't been able to find anything really useful on what to properly assign to random in the lme formula. For repeated measures the use above is always in the examples. __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] lagsarlm - using mixed explanatory variables (spdep package)
On Thu, 27 Nov 2003, Roy Sanderson wrote: Hello Usually it is easier to send package questions directly to the package maintainer, because they may not interest the whole list. I'm very new to R (which is excellent), so apologies if this has already been raised. In the spdep package, I'm trying to undertake an autoregressive mixed model using the lagsarlm function. This is working fine, but there does not appear to be a method of including an explanatory variable without it automatically being included as a lagged term. I'm after something along the lines of y = rho.W.y + x1 + x2 + lag(x2) but am only able to output y = rho.W.y + x1 + x2 + lag(x1) + lag(x2) Using the old Columbus data set in the spdep package: data(oldcol) lagsarlm(CRIME ~ INC + HOVAL, data = COL.OLD, nb2listw(COL.nb)) lagsarlm(CRIME ~ INC + HOVAL, data = COL.OLD, nb2listw(COL.nb), + type=mixed) give the standard lag and mixed model types, but you need to use type=lag and include the spatially lagged x variable(s) manually: WINC - lag.listw(nb2listw(COL.nb), COL.OLD$INC) lagsarlm(CRIME ~ INC + HOVAL + WINC, data = COL.OLD, nb2listw(COL.nb)) Hope this helps, Roger Is there any way around this issue? Many thanks Roy Roy Sanderson Centre for Life Sciences Modelling Porter Building University of Newcastle Newcastle upon Tyne NE1 7RU United Kingdom Tel: +44 191 222 7789 [EMAIL PROTECTED] http://www.ncl.ac.uk/clsm __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help -- Roger Bivand Economic Geography Section, Department of Economics, Norwegian School of Economics and Business Administration, Breiviksveien 40, N-5045 Bergen, Norway. voice: +47 55 95 93 55; fax +47 55 95 93 93 e-mail: [EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] significance in difference of proportions
On 11/27/03 17:04, [EMAIL PROTECTED] wrote: Hello, I'm looking for some guidance with the following problem: I've 2 samples A (111 items) and B (10 items) drawn from the same unknown population. Witihn A I find 9 positives and in B 0 positives. I'd like to know if the 2 samples A and B are different, ie is there a way to find out whether the number of positives is significantly different in A and B? I'm currently using prop.test, but unfortunately some of my data contains less than 5 items in a group (like in the example above), and the test statistics may not hold: fisher.test in the ctest package, which loads automatically. -- Jonathan Baron, Professor of Psychology, University of Pennsylvania Home page:http://www.sas.upenn.edu/~baron __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] significance in difference of proportions
Hello, I'm looking for some guidance with the following problem: I've 2 samples A (111 items) and B (10 items) drawn from the same unknown population. Witihn A I find 9 positives and in B 0 positives. I'd like to know if the 2 samples A and B are different, ie is there a way to find out whether the number of positives is significantly different in A and B? I'm currently using prop.test, but unfortunately some of my data contains less than 5 items in a group (like in the example above), and the test statistics may not hold: The statistic is fine, the approximation to its null distribution may be questionable :-) prop.test(c(9,0), c(111,10)) 2-sample test for equality of proportions with continuity correction data: c(9, 0) out of c(111, 10) X-squared = 0.0941, df = 1, p-value = 0.759 alternative hypothesis: two.sided 95 percent confidence interval: -0.02420252 0.18636468 sample estimates: prop 1 prop 2 0.08108108 0. Warning message: Chi-squared approximation may be incorrect in: prop.test(c(9, 0), c(111, 10)) Do you have suggestions for an alternative test? you may consider a permutation test for two independent samples: R library(exactRankTests) R x = c(rep(1, 9), rep(0, 102)) R y = rep(0, 10) R mean(x) [1] 0.08108108 R mean(y) [1] 0 R perm.test(y, x, exact = TRUE) 2-sample Permutation Test data: y and x T = 0, p-value = 0.6092 alternative hypothesis: true mu is not equal to 0 Best, Torsten many thanks for your help, +kind regards, Arne __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] significance in difference of proportions: What problem are you solving?
Hi, Torsten: Thanks for the reference to library(exactRankTests). That seems like a reasonable alternative to prop.test with small samples. However, aren't exact tests and the related bootstrap methodology what Deming called enumerative techniques, more relating to describing a fixed finite population than enumerative techniques for describing more general processes that will likely generate similar samples in the future? Don't exact tests and bootstraps answer different (enumerative) questions from those posed by standard (analytic) parametric procedures? (I know that the chi-square distribution is only an approximation to the distribution of the contingency table chi-square; however, that is a different issue from the question of enumerative vs. analytic studies.) Thanks again for this and your many other interesting contributions to r-help. Spencer Graves Torsten Hothorn wrote: Hello, I'm looking for some guidance with the following problem: I've 2 samples A (111 items) and B (10 items) drawn from the same unknown population. Witihn A I find 9 positives and in B 0 positives. I'd like to know if the 2 samples A and B are different, ie is there a way to find out whether the number of positives is significantly different in A and B? I'm currently using prop.test, but unfortunately some of my data contains less than 5 items in a group (like in the example above), and the test statistics may not hold: The statistic is fine, the approximation to its null distribution may be questionable :-) prop.test(c(9,0), c(111,10)) 2-sample test for equality of proportions with continuity correction data: c(9, 0) out of c(111, 10) X-squared = 0.0941, df = 1, p-value = 0.759 alternative hypothesis: two.sided 95 percent confidence interval: -0.02420252 0.18636468 sample estimates: prop 1 prop 2 0.08108108 0. Warning message: Chi-squared approximation may be incorrect in: prop.test(c(9, 0), c(111, 10)) Do you have suggestions for an alternative test? you may consider a permutation test for two independent samples: R library(exactRankTests) R x = c(rep(1, 9), rep(0, 102)) R y = rep(0, 10) R mean(x) [1] 0.08108108 R mean(y) [1] 0 R perm.test(y, x, exact = TRUE) 2-sample Permutation Test data: y and x T = 0, p-value = 0.6092 alternative hypothesis: true mu is not equal to 0 Best, Torsten many thanks for your help, +kind regards, Arne __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] MASS fitdistr()
Dear R experts, I am trying to use the R MASS library fitdistr() to fit the following list: k21stsList-c(0.76697,0.57642,0.75938,0.82616,0.93706,0.77377,0.58923,0.37157,0.60796,1.00070,0.97529,0.62858,0.63504,0.68697,0.61714,0.75227,1.16390,0.66702,0.83578) as follows, library(MASS) fitdistr(k21stsList, normal) But, I get Error in fitdistr(k21stsList, normal) : 'start' must be a named list What am I doing wrong (probably alot!) Thanks, Oscar __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] dvips function gives Documents not found error
This is primarily an FYI to the Hmisc author, though any brilliant suggestions from him or anyone else are always welcome. Re this problem reported earlier in this thread: getting an error from Hmisc when trying dvips(latex(describe(mtcars)),file=/kellytest/kelly.ps) that says Error in system(cmd, intern = intern, wait = wait | intern, show.output.on.console = wait, : C:/Documents not found which appears to be a path-parsing problem of Documents and Settings The problem is still present. I've tried every suggestion that was sent to me. Most recently, I created a .Renviron which said TMP=c:/kellytest/rtemp and I then ran R (from within emacs/ess). I verified that TMP had been set correctly as follows: tempdir() [1] c:/kellytest/rtemp\\Rtmp5417 but I still got the C:/Documents not found error. P.S. I found that a TeX file was created when the command was executed, but I could find no evidence of a dvi or ps file. -- David Kelly __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] MASS fitdistr()
On Thu, 27 Nov 2003, Oscar Linares wrote: Dear R experts, I am trying to use the R MASS library fitdistr() to fit the following list: Well, that is not a list! k21stsList-c(0.76697,0.57642,0.75938,0.82616,0.93706,0.77377,0.58923,0.37157,0.60796,1.00070,0.97529,0.62858,0.63504,0.68697,0.61714,0.75227,1.16390,0.66702,0.83578) as follows, library(MASS) fitdistr(k21stsList, normal) But, I get Error in fitdistr(k21stsList, normal) : 'start' must be a named list You omitted the `start' argument, and normal is not in the list specified in the Details section. What am I doing wrong (probably alot!) It always helps to read through the whole help page rather than guessing. Given that the MLEs for a normal are known explicitly, why are you doing this? -- 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 __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] lme v. aov?
Its not so much that I wasn't getting the difference between fixed and random effects. Although, I do like the way you put the comment below. For my purposes subject is a random effect. It was more on correct notation in lme with repeated measures designs (my a and b are repeated while the mean subjectRT is between). And, on whether the way aov treats repeated measures might best be called a MANOVA method. On Nov 27, 2003, at 12:54 PM, Spencer Graves wrote: Do you want to make inference about the specific subjects in your study? If yes, the subjects are a fixed effect. If instead you want to make inference about the societal processes that will generate the subjects you will get in the future, that is a random effect. The function lme handles both fixed and random effects, as does varcomp. The functions aov and lm are restricted to fixed effects only. You can use dummy coding for lm and aov as well. The the distinction between fixed and random effects seems to me to be the same as what Deming called the difference between enumerative and analytic studies: With a fixed effect / enumerative study, the objective is to determine the disposition of the sampling frame. For example, Deming managed a survey of food distribution in Japan in 1946 or so, right after World War II. The purpose was to determine where to deliver food the next day, etc., to keep people from dying of starvation. That was an enumerative study. If the purpose had been to advance economic theories for use not only in Japan or in 1946-47, that is an analytic study. Do you have the book Pinhiero and Bates (2000) Mixed-Effects Models in S and S-Plus (Springer)? If you have more than one use for analyzing data on human subjects, I suggest you get and study this book if you haven't already. Doug Bates and several of his graduate students have developed lme. I am not current in the absolute latest literature in that area of statistics, but Bates seems to me to be among the leaders in that area and specifically in statistical computing for that kind of problem. hope this helps. spencer graves John Christie wrote: I am trying to understand better an analysis mean RT in various conditions in a within subjects design with the overall mean RT / subject as one of the factors. LME seems to be the right way to do this. using something like m- lme(rt~ a *b *subjectRT, random= ~1|subject) and then anova(m,type = marginal). My understanding is that lme is an easy interface for dummy coding variables and doing a multiple regression (and that could be wrong). But, what is aov doing in this instance? MANOVA? I also haven't been able to find anything really useful on what to properly assign to random in the lme formula. For repeated measures the use above is always in the examples. __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] tcltk - tkcreate question
Hello,
i'm trying to translate following tcltk source code, which I found in
newsgroup comp.lang.tcl, written by Tom Wilkason, into R Code.
proc scrolled_Canvas {base} {
frame $base.fm -borderwidth 2 -relief sunken
canvas $base.fm.cv -yscrollcommand $base.fm.cv_vertscrollbar set
scrollbar $base.fm.cv_vertscrollbar -orient vertical \
-command $base.fm.cv yview
pack $base.fm.cv -side left -fill both -expand true
pack $base.fm.cv_vertscrollbar -side right -fill y
pack $base.fm -side top -fill both -expand true
set hull [frame $base.fm.cv.hull -borderwidth 2 -relief ridge]
set wid [winfo width $base.fm]
$base.fm.cv create window 0 0 -anchor nw -window $hull -width 10 -height 500 -tag
window
bind $base.fm.cv Configure ResizeCanvas %W %w %h
return $hull
}
I have successfully translated the code until the line
$base.fm.cv create window 0 0 -anchor nw -window $hull -width 10 -height 500 -tag
window
which i don't fully understand because i started with tcltk just this
week.
I tried to translate this line using the R function tkcreate, but i didn't
get very far.
Thanks for your help.
Greetings,
Thomas Stabla
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] tcltk - tkcreate question
Thomas Stabla [EMAIL PROTECTED] writes: I have successfully translated the code until the line $base.fm.cv create window 0 0 -anchor nw -window $hull -width 10 -height 500 -tag window which i don't fully understand because i started with tcltk just this week. I tried to translate this line using the R function tkcreate, but i didn't get very far. I assume you got the canvas ($base.fm.cv) stored in a variable, cv, say, and hull similarly. Then my first guess would be tkcreate(cv, window, 0, 0, anchor=nw, window=hull, width=10, height=5, tag= window) -- O__ Peter Dalgaard Blegdamsvej 3 c/ /'_ --- Dept. of Biostatistics 2200 Cph. N (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] tcltk - tkcreate question
On 27 Nov 2003, Peter Dalgaard wrote: Thomas Stabla [EMAIL PROTECTED] writes: I have successfully translated the code until the line $base.fm.cv create window 0 0 -anchor nw -window $hull -width 10 -height 500 -tag window which i don't fully understand because i started with tcltk just this week. I tried to translate this line using the R function tkcreate, but i didn't get very far. I assume you got the canvas ($base.fm.cv) stored in a variable, cv, say, and hull similarly. Then my first guess would be tkcreate(cv, window, 0, 0, anchor=nw, window=hull, width=10, height=5, tag= window) Works fine, thank you for your fast help. Best regards, Thomas Stabla __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] cclust - cindex - binary data
Hi, I'm trying to debug a function I wrote to calculate the cindex for a hierarchical tree. For this it is useful to compare my calculations with those in output from the clustindex function, in the cclust library. There's no way, however, to have the cindex value for a given output of the cclust function, as a NA value is always returned. This happens almost surely because the cindex in clustIndex is calculated only for binary data, but, in turn, I can't find a way to specify either with the cclust function or with the clustIndex function, that an eventual input data set is binary. Thanks a lot Bruno __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] dvips function gives Documents not found error
On Thu, 27 Nov 2003 10:04:51 -0800 David Kelly [EMAIL PROTECTED] wrote: This is primarily an FYI to the Hmisc author, though any brilliant suggestions from him or anyone else are always welcome. Re this problem reported earlier in this thread: getting an error from Hmisc when trying dvips(latex(describe(mtcars)),file=/kellytest/kelly.ps) that says Error in system(cmd, intern = intern, wait = wait | intern, show.output.on.console = wait, : C:/Documents not found which appears to be a path-parsing problem of Documents and Settings The problem is still present. I've tried every suggestion that was sent to me. Most recently, I created a .Renviron which said TMP=c:/kellytest/rtemp and I then ran R (from within emacs/ess). I verified that TMP had been set correctly as follows: tempdir() [1] c:/kellytest/rtemp\\Rtmp5417 but I still got the C:/Documents not found error. P.S. I found that a TeX file was created when the command was executed, but I could find no evidence of a dvi or ps file. -- David Kelly __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help Did you make the changes I suggested (surrounding two items by dQuote( ))? Have you tried Linux? :) --- Frank E Harrell JrProfessor and ChairSchool of Medicine Department of BiostatisticsVanderbilt University __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] Re: FDA and ICH Compliance of R
Antonia Drugica [EMAIL PROTECTED] writes: Does anybody know if R is FDA or ICH (or EMEA...) compliant? AFAIK S-Plus is but that means nothing... As Thomas pointed out, that does mean nothing -- there was a group of folks discussing what might be done to help, earlier this year, but then everyone got busy... FDA has a guidance document for off-the-shelf software: http://www.fda.gov/cdrh/ode/guidance/585.html Note that if focuses on OTS used in medical devices. However you should read it. The document: http://www.fda.gov/cdrh/comp/guidance/938.html Has a section on applicability of the software guidance (which encompasses stuff outside the instrument itself. Since I am no lawyer, I can't say whether R falls within this scope. It is fair to say however that the FDA consider safety and effectiveness very important. If the effectiveness that you claim is based on statistics provided by software, or you rely in software for determining safe levels (eg of a drug) then I would say (as a layman) it is largely irrelevant whether the vendor claims some sort of FDA badge because that does not prevent someone from writing dodgy scripts. So what you can do (other than soliciting mail list opinions) includes: o Think. What are the implications for end users, patients etc. Would you take a pill based on your own stats? o Read what the FDA have to say. o Evaluate the risk and safety implications of the statistics you use. o Manage the risk. Eg can you indepently confirm the key results? o Your scripts are software - the FDA requires evidence of a credible process in the life cycle of software, whether they be spreadsheets, real time control systems or whatever. OTS software that is validated does not remove responsibility for reducing risk to acceptable levels. HTH paul __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] dvips function gives Documents not found error
Frank Harrell wrote: Did you make the changes I suggested (surrounding two items by dQuote())? Have you tried Linux? No, I didn't make those changes because I've just been working with a binary distribution. I may go ahead and pull down sources and try; I was trying to avoid that. I wish I were working with Linux, but I'm doing this work for someone with many installed PCs that want to use R, and they're all running Win2K and that isn't going to change. Thanks for the reply - David Kelly __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] dvips function gives Documents not found error
On Thu, Nov 27, 2003 at 04:21:04PM -0800, David Kelly wrote: Frank Harrell wrote: Did you make the changes I suggested (surrounding two items by dQuote())? Have you tried Linux? No, I didn't make those changes because I've just been working with a binary distribution. I may go ahead and pull down sources and try; I was But that's the beauty of it -- even in Windoze, the $R_HOME/library/$FOO/R/ directory for a package $FOO contains simple text code which you can edit. If you know how to read and write S source code, I may take you only about one minute to locate the file, and insert the suggested dQuote(). trying to avoid that. I wish I were working with Linux, but I'm doing this work for someone with many installed PCs that want to use R, and they're all running Win2K and that isn't going to change. If you organise your work environment wel, operating systems matter less and less. R, Perl, Python, ... are pretty much completely cross-platform (unless you insist on using OS-specific features). Dirk -- Those are my principles, and if you don't like them... well, I have others. -- Groucho Marx __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
