Re: [R] R and clinical studies
Delphine, Please see the following message posted a week ago: http://comments.gmane.org/gmane.comp.lang.r.general/80175. HTH, -Mat -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Delphine Fontaine Sent: Friday, March 09, 2007 8:29 AM To: r-help@stat.math.ethz.ch Subject: [R] R and clinical studies Does anyone know if for clinical studies the FDA would accept statistical analyses performed with R ? Delphine Fontaine __ 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 and provide commented, minimal, self-contained, reproducible code. __ 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 and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using R for devices trial
Hi Cody, I would point you to the presentation by Sue Bell at least year's ASA meeting available here: http://www.fda.gov/Cder/Offices/Biostatistics/Bell.pdf. I can't speak for CDRH, but at CDER we are making some progress towards the level of comfort with the use of R as a valid software tool. Specifically, 1. R was granted approval by our IT folks for use on our government PC's (2 years in the making to get this). 2. An R course is in development for FDA reviewers to use R for review of clinical trial data. 3. This Monday at the 1st FDA/DIA Spring Meeting I will be offering a tutorial on Statistical Graphics with R for Clinical Trial Data. 4. An increasing effort to pigeon-tail R to ongoing projects to show proof by example that R can be trusted when used properly. So from the regulatory side, progress is being made, but there still do exist those who have some discomfort with the use of an open-source tool for data analysis. Someday hopefully that too will be changed. HTH, -Mat Disclaimer: The views expressed are those of the author and must not be taken to represent policy or guidance on behalf of the Food and Drug Administration. -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of [EMAIL PROTECTED] Sent: Thursday, March 01, 2007 5:43 PM To: [EMAIL PROTECTED] Subject: [R] Using R for devices trial I would like to use R for submissions to FDA/CDRH (the medical device company I work for currently uses only SAS). Previous postings to the list regarding R and 21 CFR 11 compliance have been very helpful. However, reluctance to using open source software for statistical analyses and reporting remains high here at my company. Has anyone used R for an official submission to FDA/CDRH? It would be most helpful if I could tell our group that others have been able to use R for this purpose. Regards, Cody Hamilton Staff Biostatistician Edwards Lifesciences __ 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 and provide commented, minimal, self-contained, reproducible code. __ 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 and provide commented, minimal, self-contained, reproducible code.
[R] Version of R in saved workspaces
useRs and developeRs- Apologies for my naivety, but I just couldn't figure out how to open an old workspace (created using R 2.3.0) using R 2.3.0 and not R 2.4.0 which is currently happening. For all I know this has always been the case, but I'm having a problem with a function that doesn't work in 2.4.0 but does work in 2.3.1 (function is in the process of being fixed). So I would ideally like to open my old workspaces with the version of R I used in creating the workspace and at the moment not in R 2.4.0 - though in a few weeks when the function is fixed I'm sure I'll love 2.4.0 as I have all previous versions:) Thanks for any help, -Mat Steps to what I'm doing. 1. In R 2.3.1 I import data, manipulate it until my heart's content, and run some analyses. 2. I save the workspace to my local drive - name it CoolStats.RData. 3. I see R 2.4.0 is released and immediately download it and start playing with it only to find the above mentioned error. 4. Since error is going to take some time to fix, will work with R 2.3.1 in the interim. 5. Open CoolStat.Rdata and when I type version I get the below. version _ platform i386-pc-mingw32 arch i386 os mingw32 system i386, mingw32 status major 2 minor 4.0 year 2006 month 10 day03 svn rev39566 language R version.string R version 2.4.0 (2006-10-03) *** Mat Soukup, Ph.D. Food and Drug Administration 10903 New Hampshire Ave. BLDG 22 RM 5329 Silver Spring, MD 20993-0002 Phone: 301.796.1005 *** [[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 and provide commented, minimal, self-contained, reproducible code.
[R] [Off-Topic-but somewhat related] DIA/FDA Open Toolbox Initiative
UseR's- As this is slightly off-topic I will limit the discussion to only the major points; for further information feel free to reply off-line. DIA and FDA are hosting a forum to discuss (as per the Goal of the announcement--see link below) a vendor-neutral software product to support validated analytic procedures (tools) and make tool development a collaborative effort among reviewers, academic researchers, and the pharmaceutical industry. The analytic procedures could be done in R. SAS (gasp), Stata, Splus, or other programming language. This is just an initiative and the hope is to attract people that would like to contribute to the effort and also assist in guiding the direction of the development of such software. This is a free event held on Sept. 14, 2006 in Bethesda, Maryland (Washington DC area). Space is limited to the first 30 to register, so if interested please do so early. For further details including how to register please see the following link. http://www.diahome.org/DIAHome/Education/FindEducationalOffering.aspx?pr oductID=12092eventType=Meeting Thank you and apologies for the off-topic post, but I felt this might be of interest to some of the many great UseRs. Cheers, -Mat Standard Disclaimer: The views and opinions expressed are those of the author and not those of the FDA. *** Mat Soukup, Ph.D. Food and Drug Administration 10903 New Hampshire Ave. BLDG 22 RM 5329 Silver Spring, MD 20993-0002 Phone: 301.796.1005 *** [[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 and provide commented, minimal, self-contained, reproducible code.
[R] trellis.focus with postscript device
Hello. First: R 2.3.1 on Windows XP. I am trying to add information (sample size) to the Trellis strips which I am successful using the trellis.focus function with the default Windows device. However, I typically use the postscript device as I use LaTeX and \includegraphic for incorporating graphs into stat reviews. Here's some example code (apologies for the lack of creativity and resemblance to a real example) yy - c(rnorm(20,2),rnorm(35,3), rnorm(30,2),rnorm(20,3),rnorm(4,2), rnorm(10,3)) xx - c(1:20,1:35,1:30,1:20,1:4,1:10) gg - rep(c('A','B','A','B','A','B'), c(20,35,30,20,4,10)) pp - rep(c('Cond 1','Cond 2','Cond 3'), c(55, 50, 14)) xyplot(yy ~ xx | pp, groups=gg) trellis.focus('strip', 1, 1) ltext(0,.5,'20',col='red', pos=4) ltext(1,.5,'35',col='black', pos=2) trellis.unfocus() trellis.focus('strip', 2, 1) ltext(0,.5,'30',col='red', pos=4) ltext(1,.5,'20',col='black', pos=2) trellis.unfocus() trellis.focus('strip', 1, 2) ltext(0,.5,'4',col='red', pos=4) ltext(1,.5,'10',col='black', pos=2) trellis.unfocus() This works. But if I do, postscript('C:/TEMP/example.eps') # All code as above dev.off() I notice a problem with the graphic. When looking at the EPS figure, the only strip with added data is the first one (bottom left) with the strip still highlighted in red (i.e. it doesn't appear that trellis.unfocus() was executed). Work arounds that I can think of are to simply save the Windows device as postscript and save to the correct directory or better yet, write my own strip function. However, I was curious if there was another way using the strategy of postscript(), graph code, trellis.focus() code, dev.off(). Thanks, Mat *** Mat Soukup, Ph.D. Food and Drug Administration 10903 New Hampshire Ave. BLDG 22 RM 5329 Silver Spring, MD 20993-0002 Phone: 301.796.1005 *** [[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 and provide commented, minimal, self-contained, reproducible code.
Re: [R] trellis.focus with postscript device
Thanks Deepayan. Adding the argument highlight=FALSE to each trellis.focus() call worked marvelously. Cheers, Mat -Original Message- From: Deepayan Sarkar [mailto:[EMAIL PROTECTED] Sent: Wednesday, July 19, 2006 11:58 AM To: Soukup, Mat Cc: r-help@stat.math.ethz.ch Subject: Re: [R] trellis.focus with postscript device On 7/19/06, Soukup, Mat [EMAIL PROTECTED] wrote: Hello. First: R 2.3.1 on Windows XP. I am trying to add information (sample size) to the Trellis strips which I am successful using the trellis.focus function with the default Windows device. However, I typically use the postscript device as I use LaTeX and \includegraphic for incorporating graphs into stat reviews. Here's some example code (apologies for the lack of creativity and resemblance to a real example) yy - c(rnorm(20,2),rnorm(35,3), rnorm(30,2),rnorm(20,3),rnorm(4,2), rnorm(10,3)) xx - c(1:20,1:35,1:30,1:20,1:4,1:10) gg - rep(c('A','B','A','B','A','B'), c(20,35,30,20,4,10)) pp - rep(c('Cond 1','Cond 2','Cond 3'), c(55, 50, 14)) xyplot(yy ~ xx | pp, groups=gg) trellis.focus('strip', 1, 1) ltext(0,.5,'20',col='red', pos=4) ltext(1,.5,'35',col='black', pos=2) trellis.unfocus() trellis.focus('strip', 2, 1) ltext(0,.5,'30',col='red', pos=4) ltext(1,.5,'20',col='black', pos=2) trellis.unfocus() trellis.focus('strip', 1, 2) ltext(0,.5,'4',col='red', pos=4) ltext(1,.5,'10',col='black', pos=2) trellis.unfocus() This works. But if I do, postscript('C:/TEMP/example.eps') # All code as above dev.off() I notice a problem with the graphic. When looking at the EPS figure, the only strip with added data is the first one (bottom left) with the strip still highlighted in red (i.e. it doesn't appear that trellis.unfocus() was executed). Actually, you have produced a multiple-page postscript file, with what you really want in the last page. If you highlight the strips when calling trelis.focus, they have to be un-highlighted by trellis.unfocus. In theory, this is just a removal of a rectangle object. In practice, grid achieves this by drawing a new page. You need to avoid this. Your options are: (1) add 'highlight = FALSE' to all trellis.focus() calls (2) run the script in batch mode, where the default highlight = interactive() is FALSE I'll think about adding an option to control the default. Deepayan __ 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 and provide commented, minimal, self-contained, reproducible code.
Re: [R] generating LaTeX tables from Match output
Hi Brian, I think the following should work, although this may not be the most elegant solution. dat - matrix(c(a$est, b$est,a$se, b$se), ncol=2) colnames(dat) - c('Estimate','SE') latex(dat, file='C:/Temp/out.tex', rowlabel='', digits=3) HTH, -Mat -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Brian Quinif Sent: Tuesday, April 04, 2006 2:05 PM To: r-help@stat.math.ethz.ch Subject: [R] generating LaTeX tables from Match output Dear R users, I am using the Match function to generate nearest neighbor matching estimators. On that front I am ok, but where I am having problems is getting my output into nice LaTeX tables. Here is some basic code imitating the estimation I'm doing. No problem there. library(Matching) #make up some data X1 - matrix(rnorm(1000*5), ncol=5) Y1 - as.vector(rnorm(1000)) Tr1 - c(rep(1,500),rep(0,500)) #estimate nearest neighbor, 1-1 matching, ATT a - Match(Y=Y1, X=X1, Tr=Tr1, M=1) summary(a) #make up some more data X2 - matrix(rnorm(1000*5), ncol=5) Y2 - as.vector(rnorm(1000)) Tr2 - c(rep(1,500),rep(0,500)) b - Match(Y=Y2, X=X2, Tr=Tr2, M=1) summary(b) I have tried the xtable and latex functions but have not been able to get what I wanted. One thing you should know if you are unfamiliar with Match is that it only generates *one* estimator. What I want to do is take the coefficient a (along with its SE) and the coefficient in b (along with its SE) and put them into a nice table. Once I get that accomplished, I'll worry about titles, etc. Eventually, though, I will want to put the results from many (say, 10) estimations in one table. If anyone has some recommended code, I'd really appreciate it. Thanks, Brian __ 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] Potential for R to conflict with other softwares
Hi. After some time, my collegues at the Food and Drug Adminstration have finally acknowledged R as a powerful statistical computing environment. However, in order to comply with the Office of Information and Technology standards there are a couple of questions about whether R could interfere with other software. As I'm more of a driver of the R software and not a mechanic, I was hoping for the insight of the many great useRs. Below is a list of 5 proposed questions to which I value any comment. Thank you for your time, -Mat 1. Does R have high resolution graphics? 2. Does R have .dll files, or other executables which are not located in the R software directory tree? 3. Does R modify the Windows registry in a non-obvious way, i.e. other than defining itself and what extensions to associate with R, and what are those extensions? 4. Does R add macros to any part of MS Office? 5. Can you anticipate any other way in which installing and using R could disrupt the operation of another software? *** Mat Soukup, Ph.D. Food and Drug Administration 10903 New Hampshire Ave. BLDG 22 RM 5329 Silver Spring, MD 20993-0002 Phone: 301.796.1005 *** [[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] Potential for R to conflict with other softwares
I just wanted to make one clarification about my statement: After some time, my collegues at the Food and Drug Adminstration have finally acknowledged R as a powerful statistical computing environment. I did not intend for this to read that R has been acknowledged as being 21 CFR Part 11 compliant. This is a whole other ball game. What I meant to say is that, within the Center of Drug Evaluation and Research (CDER) the Office of Biostatistics is willing to look into whether or not reviewers can download R onto their government issued PC's. And this must all be approved by the Office of Information and Technology. So admittedly, this is only a small step, but nonetheless it is a step in the right direction. I apologize for any confusion. Cheers, Mat Disclaimer which I also forgot in the original post: The following views are those of the writer and do not necessarily reflect those of the FDA. -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Duncan Murdoch Sent: Thursday, November 03, 2005 6:30 AM To: Soukup, Mat Cc: 'r-help@stat.math.ethz.ch' Subject: Re: [R] Potential for R to conflict with other softwares On 11/3/2005 9:11 AM, Soukup, Mat wrote: Hi. After some time, my collegues at the Food and Drug Adminstration have finally acknowledged R as a powerful statistical computing environment. However, in order to comply with the Office of Information and Technology standards there are a couple of questions about whether R could interfere with other software. As I'm more of a driver of the R software and not a mechanic, I was hoping for the insight of the many great useRs. Below is a list of 5 proposed questions to which I value any comment. Thank you for your time, -Mat These answers are about the Windows version only, but from the questions, I think that's what you were looking for. They apply to all versions since 1.6.x at least (though the earlier ones would have put fewer entries into the registry, they put them in the same places). 1. Does R have high resolution graphics? Yes, but I don't think I get the point of this question. How would that interfere with other software? 2. Does R have .dll files, or other executables which are not located in the R software directory tree? No, it installs everything below R_HOME. 3. Does R modify the Windows registry in a non-obvious way, i.e. other than defining itself and what extensions to associate with R, and what are those extensions? I think all of its modifications would count as obvious. They are mainly below HKLM/Software/R-core or HKCU/Software/R-core (where the file locations are recorded); additionally file associations are set up for .Rdata files (which are called RWorkspace files there), and an uninstall entry is made. 4. Does R add macros to any part of MS Office? No. 5. Can you anticipate any other way in which installing and using R could disrupt the operation of another software? No, not really. Maybe users will become addicted to it? ;-) Duncan Murdoch ** * Mat Soukup, Ph.D. Food and Drug Administration 10903 New Hampshire Ave. BLDG 22 RM 5329 Silver Spring, MD 20993-0002 Phone: 301.796.1005 ** * [[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