Re: [R] Troubles plotting lrm output in Design Library
2008/5/29 Frank E Harrell Jr [EMAIL PROTECTED]: Patrizio Frederic wrote: dear Harrell, thank you for quick reply and suggestions. I still have the problem: library(Design) x = rnorm(100) y = runif(100)(exp(x)/(1+exp(x))) y = 0*y+1*y d = datadist(x,y) options(datadist=d) fit = lrm(y~x) # works fine, but plot(fit) #produce the error message I cannot reproduce the error on Linux R 2.7.0 using the same version of the packages you are using. Frank just for the records, I solved the problem: in Windows R 2.7.0 one has to set: d = datadist(x,y) .Options$datadist=d done that functions summary.Design, and plot.Design work fine. PF __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Troubles plotting lrm output in Design Library
Patrizio Frederic wrote: 2008/5/29 Frank E Harrell Jr [EMAIL PROTECTED]: Patrizio Frederic wrote: dear Harrell, thank you for quick reply and suggestions. I still have the problem: library(Design) x = rnorm(100) y = runif(100)(exp(x)/(1+exp(x))) y = 0*y+1*y d = datadist(x,y) options(datadist=d) fit = lrm(y~x) # works fine, but plot(fit) #produce the error message I cannot reproduce the error on Linux R 2.7.0 using the same version of the packages you are using. Frank just for the records, I solved the problem: in Windows R 2.7.0 one has to set: d = datadist(x,y) .Options$datadist=d done that functions summary.Design, and plot.Design work fine. PF Thanks for the solution. But I wish someone would tell us why the solution makes sense. If you have changed your R environment in any way from the defaults please let us know. Frank -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org 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] Troubles plotting lrm output in Design Library
Thanks for the solution. But I wish someone would tell us why the solution makes sense. If you have changed your R environment in any way from the defaults please let us know. Frank -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University dear Harrell and R users, It took me several hours to figure out. I apologize it was my mistake. Few month ago a modified copy of .Options was created in Rprofile (I don't remember why). The copy masked the alias .Options created by options(). Now everything is fixed. Now I know how .Options and options are related one each other. Sorry for wasting your time. Thank you for your help. Patrizio Frederic __ R-help@r-project.org 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] Troubles plotting lrm output in Design Library
Patrizio Frederic wrote: Thanks for the solution. But I wish someone would tell us why the solution makes sense. If you have changed your R environment in any way from the defaults please let us know. Frank -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University dear Harrell and R users, It took me several hours to figure out. I apologize it was my mistake. Few month ago a modified copy of .Options was created in Rprofile (I don't remember why). The copy masked the alias .Options created by options(). Now everything is fixed. Now I know how .Options and options are related one each other. Sorry for wasting your time. Thank you for your help. Patrizio Frederic That's great news. Thanks for figuring this out. Frank -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org 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] Troubles plotting lrm output in Design Library
On Fri, 30 May 2008, Patrizio Frederic wrote: Thanks for the solution. But I wish someone would tell us why the solution makes sense. If you have changed your R environment in any way from the defaults please let us know. Frank -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University dear Harrell and R users, It took me several hours to figure out. I apologize it was my mistake. Few month ago a modified copy of .Options was created in Rprofile (I don't remember why). The copy masked the alias .Options created by options(). Now everything is fixed. Now I know how .Options and options are related one each other. Sorry for wasting your time. Thank you for your help. This is an infelicity in Design and Hmisc (and a few other packages), in that they do look at the first visible .Options. R itself only looks at the copy in the symbol table (which also appears in the base namespace). -- 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@r-project.org 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] Troubles plotting lrm output in Design Library
Prof Brian Ripley wrote: On Fri, 30 May 2008, Patrizio Frederic wrote: Thanks for the solution. But I wish someone would tell us why the solution makes sense. If you have changed your R environment in any way from the defaults please let us know. Frank -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University dear Harrell and R users, It took me several hours to figure out. I apologize it was my mistake. Few month ago a modified copy of .Options was created in Rprofile (I don't remember why). The copy masked the alias .Options created by options(). Now everything is fixed. Now I know how .Options and options are related one each other. Sorry for wasting your time. Thank you for your help. This is an infelicity in Design and Hmisc (and a few other packages), in that they do look at the first visible .Options. R itself only looks at the copy in the symbol table (which also appears in the base namespace). I hadn't thought of that. Thanks Brian. I think of .Options$foo as being faster. Is there a preferred approach other than options('foo')? Thanks Frank -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Troubles plotting lrm output in Design Library
On Fri, 30 May 2008, Frank E Harrell Jr wrote: Prof Brian Ripley wrote: On Fri, 30 May 2008, Patrizio Frederic wrote: Thanks for the solution. But I wish someone would tell us why the solution makes sense. If you have changed your R environment in any way from the defaults please let us know. Frank -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University dear Harrell and R users, It took me several hours to figure out. I apologize it was my mistake. Few month ago a modified copy of .Options was created in Rprofile (I don't remember why). The copy masked the alias .Options created by options(). Now everything is fixed. Now I know how .Options and options are related one each other. Sorry for wasting your time. Thank you for your help. This is an infelicity in Design and Hmisc (and a few other packages), in that they do look at the first visible .Options. R itself only looks at the copy in the symbol table (which also appears in the base namespace). I hadn't thought of that. Thanks Brian. I think of .Options$foo as being faster. Is there a preferred approach other than options('foo')? getOption(foo). Because .Options is a pairlist, the speed can be illusory. Thanks Frank -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University -- 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@r-project.org 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] Troubles plotting lrm output in Design Library
dear Harrell, thank you for quick reply and suggestions. I still have the problem: library(Design) x = rnorm(100) y = runif(100)(exp(x)/(1+exp(x))) y = 0*y+1*y d = datadist(x,y) options(datadist=d) fit = lrm(y~x) # works fine, but plot(fit) #produce the error message Error in value.chk(at, ix, xseq, if (plot.type == curves) 100 else 40, : variable x does not have limits defined by datadist The installed Design (ver. 2.1.1) package was downloaded and installed via utils:::menuInstallPkgs() function (Package Hmisc version 3.4-3) on a windows xp machine. Thank in advance. Patrizio Frederic version platform i386-pc-mingw32 arch i386 os mingw32 system i386, mingw32 status major 2 minor 7.0 year 2008 month 04 day22 svn rev45424 language R version.string R version 2.7.0 (2008-04-22) 2008/5/29 Frank E Harrell Jr [EMAIL PROTECTED]: Patrizio Frederic wrote: Dear R-helpers, I'm having a problem in using plot.design in Design Library. Tho following example code produce the error: n - 1000# define sample size set.seed(17) # so can reproduce the results age- rnorm(n, 50, 10) blood.pressure - rnorm(n, 120, 15) cholesterol- rnorm(n, 200, 25) sex- factor(sample(c('female','male'), n,TRUE)) label(age)- 'Age' # label is in Hmisc label(cholesterol)- 'Total Cholesterol' label(blood.pressure) - 'Systolic Blood Pressure' label(sex)- 'Sex' units(cholesterol)- 'mg/dl' # uses units.default in Hmisc units(blood.pressure) - 'mmHg' # Specify population model for log odds that Y=1 L - .4*(sex=='male') + .045*(age-50) + + (log(cholesterol - 10)-5.2)*(-2*(sex=='female') + 2*(sex=='male')) # Simulate binary y to have Prob(y=1) = 1/[1+exp(-L)] y - ifelse(runif(n) plogis(L), 1, 0) ddist - datadist(age, blood.pressure, cholesterol, sex) options(datadist='ddist') fit - lrm(y ~ blood.pressure + sex * (age + rcs(cholesterol,4)), +x=TRUE, y=TRUE) par(mfrow=c(2,2)) plot(fit)# Plot effects of all 4 predictors Error in value.chk(at, ix, xseq, if (plot.type == curves) 100 else 40, : variable blood.pressure does not have limits defined by datadist I guess somthing goes wrong with function datadist version _ platform i386-pc-mingw32 arch i386 os mingw32 system i386, mingw32 status major 2 minor 7.0 year 2008 month 04 day22 svn rev45424 language R version.string R version 2.7.0 (2008-04-22) thank you in advance, Patrizio Frederic This is the example run by example(plot.Design) which works for me, using the version of Design from CRAN. You don't need to include code that is already in an example in a help file, and if you do please make the code copy and paste-able instead of putting something at the start of each line. Frank Frank - | Patrizio Frederic | Research associate in Statistics, | Department of Economics, | University of Modena and Reggio Emilia, | Via Berengario 51, | 41100 Modena, Italy | | tel: +39 059 205 6727 | fax: +39 059 205 6947 | mail: [EMAIL PROTECTED] +- __ R-help@r-project.org 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. -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org 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] Troubles plotting lrm output in Design Library
Patrizio Frederic wrote: dear Harrell, thank you for quick reply and suggestions. I still have the problem: library(Design) x = rnorm(100) y = runif(100)(exp(x)/(1+exp(x))) y = 0*y+1*y d = datadist(x,y) options(datadist=d) fit = lrm(y~x) # works fine, but plot(fit) #produce the error message I cannot reproduce the error on Linux R 2.7.0 using the same version of the packages you are using. Frank Error in value.chk(at, ix, xseq, if (plot.type == curves) 100 else 40, : variable x does not have limits defined by datadist The installed Design (ver. 2.1.1) package was downloaded and installed via utils:::menuInstallPkgs() function (Package Hmisc version 3.4-3) on a windows xp machine. Thank in advance. Patrizio Frederic version platform i386-pc-mingw32 arch i386 os mingw32 system i386, mingw32 status major 2 minor 7.0 year 2008 month 04 day22 svn rev45424 language R version.string R version 2.7.0 (2008-04-22) 2008/5/29 Frank E Harrell Jr [EMAIL PROTECTED]: Patrizio Frederic wrote: Dear R-helpers, I'm having a problem in using plot.design in Design Library. Tho following example code produce the error: n - 1000# define sample size set.seed(17) # so can reproduce the results age- rnorm(n, 50, 10) blood.pressure - rnorm(n, 120, 15) cholesterol- rnorm(n, 200, 25) sex- factor(sample(c('female','male'), n,TRUE)) label(age)- 'Age' # label is in Hmisc label(cholesterol)- 'Total Cholesterol' label(blood.pressure) - 'Systolic Blood Pressure' label(sex)- 'Sex' units(cholesterol)- 'mg/dl' # uses units.default in Hmisc units(blood.pressure) - 'mmHg' # Specify population model for log odds that Y=1 L - .4*(sex=='male') + .045*(age-50) + + (log(cholesterol - 10)-5.2)*(-2*(sex=='female') + 2*(sex=='male')) # Simulate binary y to have Prob(y=1) = 1/[1+exp(-L)] y - ifelse(runif(n) plogis(L), 1, 0) ddist - datadist(age, blood.pressure, cholesterol, sex) options(datadist='ddist') fit - lrm(y ~ blood.pressure + sex * (age + rcs(cholesterol,4)), +x=TRUE, y=TRUE) par(mfrow=c(2,2)) plot(fit)# Plot effects of all 4 predictors Error in value.chk(at, ix, xseq, if (plot.type == curves) 100 else 40, : variable blood.pressure does not have limits defined by datadist I guess somthing goes wrong with function datadist version _ platform i386-pc-mingw32 arch i386 os mingw32 system i386, mingw32 status major 2 minor 7.0 year 2008 month 04 day22 svn rev45424 language R version.string R version 2.7.0 (2008-04-22) thank you in advance, Patrizio Frederic This is the example run by example(plot.Design) which works for me, using the version of Design from CRAN. You don't need to include code that is already in an example in a help file, and if you do please make the code copy and paste-able instead of putting something at the start of each line. Frank Frank - | Patrizio Frederic | Research associate in Statistics, | Department of Economics, | University of Modena and Reggio Emilia, | Via Berengario 51, | 41100 Modena, Italy | | tel: +39 059 205 6727 | fax: +39 059 205 6947 | mail: [EMAIL PROTECTED] +- __ R-help@r-project.org 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. -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org 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.