Re: [R] c-statiscs 95% CI for cox regression model

example at the bottom) Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-h

Re: [R] UseR! 2010 - my impressions

e terrific (thanks to the program committee and the speakers) and Kate Mullen and her team did an extraordinary job in putting the conference together and running it. I am proud to have been a part of it. Thank you all! Frank -- Frank E Harrell Jr Professor and ChairmanSchool o

Re: [R] Problem with offset (Glm or glmD) in Design library

___ 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 ChairmanSc

Re: [R] R's Data Dredging Philosophy for Distribution Fitting

(as in checking goodness of fit of various parametric distributions), your final estimators will have the variance of empirical estimators. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University

Re: [R] SAS Proc summary/means as a R function

on; some perl code perl off; also sas on; some SAS code sas off; The purpose of parmbuff is to turn off of Rs scanning and resolution of function arguments and just provide the bare text between '(' and ')' in the function call. This is a very powerful construct

Re: [R] Function similar to combine.levels in Hmisc package

(>|t|) value using the linear model, then deleting the non-significant levels. Any other suggestions? Thanks, Saeed That is not a valid statistical procedure. You will not have the correct d.f. in the final F test. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medic

Re: [R] how to plot two histograms overlapped in the same plane coordinate

www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ 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 com

Re: [R] Visualization of coefficients

//asrr.r-forge.r-project.org/rghuang.html -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org mailing list https://stat.ethz.ch/ma

Re: [R] rms::ols & I(.) in formulas

contained, reproducible code. -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-

Re: [R] ROC curve in R

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 ChairmanSchool of Medicine Department of Biostatistics V

Re: [R] Logistic regression with multiple imputation

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 Harr

Re: [R] Wilcoxon signed rank test and its requirements

You still are stating the effect of the central limit theorem incorrectly. Please see my previous note. Frank On 06/25/2010 10:27 AM, Joris Meys wrote: > 2010/6/25 Frank E Harrell Jr: >> The central limit theorem doesn't help. It just addresses type I error, >> not power

Re: [R] Wilcoxon signed rank test and its requirements

gt; >> i would like to test, whether the mean of the sample differ significantly >> from the population mean. >> > According to probability theory, this will be in 5% of the cases if > you repeat your sampling infinitly. But as David asked: why on earth > do y

Re: [R] Wilcoxon signed rank test and its requirements

e indicator (0/1) of xi + xj > 0. So WSR tests H0:p=0.5 where p = the probability that the average of a randomly chosen pair of values is positive. [If there are ties this probably needs to be worded as P[xi + xj > 0] = P[xi + xj < 0], i neq j. Frank -- Frank E Harrell Jr Profess

Re: [R] glm

posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University ___

Re: [R] Popularity of R, SAS, SPSS, Stata...

y of SAS serving hundreds of users. Cheers, Bob Ted. E-Mail: (Ted Harding) Fax-to-email: +44 (0)870 094 0861 Date: 20-Jun-10 Time: 20:41:43 ---------- XFMail

Re: [R] Extracting P-values from the lrm function in the rms library

special case where each variable has only one degree of freedom. Just do a <- anova(mod.poly3) and treat the result as matrix. You'll get the needed multiple degree of freedom test and P-value. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine

Re: [R] Fitting a polynomial using lrm from the Design library

y ideal result. That would be log(odds) = 0 or OR=1. I wonder how many other errors I committed? Best to convert to the rms package - see http://biostat.mc.vanderbilt.edu/Rrms for differences with Design. If using ordinary polynomials, use e.g. mod.poly3 <- lrm(trait ~ pol(PC1, 3), dat

Re: [R] Latex problem in Hmisc (3.8-1) and Mac Os X with R 2.11.1

g as the ctable=T was included), but without it latex (s6) ##I do get a nicely formated table, but again the numbers are all wrong... Also ##latex(s6, long=TRUE, prmsd=TRUE, msdsize="smaller",middle.bold=TRUE) ##makes no difference from latex(s6) alone with regards

Re: [R] Is there a non-parametric repeated-measures Anova in R ?

he rank of Y and reduces to the regular nonparametric tests as special cases. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r

Re: [R] R licensing query

ter system here. My only other option for data anlaysis is Excel, we have no money for S-plus or any other stats programme. Can anyone suggest anything or send me a suitable email? Many thanks, Georgina -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine

Re: [R] Is there a non-parametric repeated-measures Anova in R ?

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 ChairmanSchool of Medicine Department of Biostatisti

Re: [R] ols function in rms package

has already been shown to be poor in many cases. You might run the following in parallel: full model fits and penalized least squares using penalties selected by AIC (using special arguments to ols along with the pentrace function). Frank Regards, Mark -- Frank E Harrel

Re: [R] ols function in rms package

If you indeed need variable selection see if backwards stepdown works for you. It is built-in to rms bootstrap validation and calibration functions. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt Unive

Re: [R] Continous variables with implausible transformation?

se lrm(Y ~ pol(x, 2)) Frank -- -- Joris Meys Statistical Consultant Ghent University Faculty of Bioscience Engineering Department of Applied mathematics, biometrics and process control Coupure Links 653 B-9000 Gent -- Frank E Harrell Jr Professor and Chairm

Re: [R] ICD9 codes

g held by the moderator. So I assumed that the question was never posted and I reposted with different subject lines just to make sure that it gets posted. I sincerely apologise for the inconvenience caused. Regards, Vishwanath On Sat, May 29, 2010 at 4:10 AM, Frank E Harrell Jr wrote: Your note

Re: [R] latex.rms and models fit with Gls

On 05/28/2010 05:31 PM, Dylan Beaudette wrote: On Friday 28 May 2010, Frank E Harrell Jr wrote: On 05/28/2010 03:49 PM, Dylan Beaudette wrote: Hi, I have fit a model using the rms package with the Gls() function. Is there a way to get the model estimates, std errors, and p-values (i.e. what

Re: [R] ICD9 codes

work with ICD9 codes. Is anyone aware of any R method that deals with ICD9 codes verification and manipulation. Thanks Vishwanath -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vander

Re: [R] latex.rms and models fit with GLS

simple way to get a table of estimated coeficients without hand-making a table in a text editor for inclusion within a LATEX document. Thanks! -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Va

Re: [R] median test

__ 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

Re: [R] median test

p://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University ___

Re: [R] Problem with plotting survival predictions from cph model

n.enter' not found" Actually, using 'survest(f, time=3)' has the same result. Has anybody encountered this kind of error? Is there a workaround? Best regards, Please provide a tiny self-contained reproducible example, e.g., using simulated data. Frank -- Frank E Harrel

Re: [R] validation logistic regression

ble code. __ 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, reproducib

Re: [R] validation logistic regression

ling 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 ChairmanSchool of Medicine

Re: [R] Relative Risk/Hazard Ratio plots for continuous variables

native HTML version deleted]] __ 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] ROC curve

cts (which it almost never is). Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo

Re: [R] Re : Re : Re : Nomogram with multiple interactions (package rms)

variable to a constant in the newdata argument to predict, and not using that variable to predict the linear predictor. Then you can make a nomogram from the ols model. Frank - Message d'origine De : Frank E Harrell Jr À : Marc Carpentier Cc : r-help-request Mailing List

Re: [R] Regression with sparse matricies

with the source package, the see what is needed in lrm to use it. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org mai

Re: [R] Re : Re : Nomogram with multiple interactions (package rms)

previous mail) I didn't see any example of this "adjustement" of nomogram to 'male' or 'female'... I hope I gave a clearer explanation and I'm not wrong about this unmentioned case. Marc - Message d'origine De : Frank E Harrell Jr À : Marc

Re: [R] Re : Nomogram with multiple interactions (package rms)

continuous predictors have two axes each, with male and female in close proximity. Or maybe I'm just missing your point. Frank - Message d'origine De : Frank E Harrell Jr À : Marc Carpentier; r-help-request Mailing List Envoyé le : Mer 19 mai 2010, 22h 28min 51s Objet :

Re: [R] Nomogram with multiple interactions (package rms)

er one But nomogram() still wants me to define interact=list(...) Thanks for any advice you might have (with adj.to or any alternative...) Marc Carpentier -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbi

Re: [R] Generating all possible models from full model

On 05/19/2010 01:39 PM, Ben Bolker wrote: Frank E Harrell Jr Vanderbilt.Edu> writes: Please read the large number of notes in the e-mail archive about the invalidity of such modeling procedures. Frank I'm curious: do you have an objection to multi-model averaging a la

Re: [R] Generating all possible models from full model

month+coslunar+sinlunar+plankton, data=mydata)) m234567<-glm.convert(glm.nb(mantas~year+cosmonth+sinmonth+coslunar+sinlunar+plankton, data=mydata)) #Seven terms - 1 model m1234567<-glm.convert(glm.nb(mantas~site*year+cosmonth+sinmonth+coslunar+sinlunar+plankton, data=myda

Re: [R] Box-Cox Transformation: Drastic differences when varying added constants

sform-both-sides nonparametric regression approaches. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org mailing list

Re: [R] Getting dates in an SPSS file in right format.

93 13071 The spss.get function in the Hmisc package handles SPSS dates. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.o

Re: [R] Simple question on binning data

practice in spectral analysis and ANPOW. ... Bert is correct. Binning is seldom needed and usually distorts. It is the statistical equivalent of a former governor from Alaska. Frank ... Sincerely, KeithC. My experience in time series is limited so I'll defer to others. Frank -- Frank E Ha

Re: [R] Cubic B-spline, how to numerically integrate?

lines. Derivatives and antiderivatives are trivial to write down. The Hmisc package has rcspline.eval and rcspline.restate functions to help, the latter having an option to express the antiderivative in text form. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Med

Re: [R] read table for Fisher Exact

id not approach 0.05 even for sample sizes over 100.'';conservativeness of ``exact'' methods;see \emph{Stat in Med} \textbf{28}:173-179, 2009 for a criticism which was unanswered} } - Original Message From: Frank E Harrell Jr To: r-help@r-project.org Sent: T

Re: [R] Simple question on binning data

from that continuous variable, then ?cut can help you. george5000 wrote: Hello everyone, I have a data set, and I need to bin my data using a bin width of say g(n). Would anyone be willing to tell me how to do this in R? Thanks -- Frank E Harrell Jr Professor and Chairman

Re: [R] read table for Fisher Exact

his case, Fisher's exact test has a good chance of being less accurate than an approximate Pearson chi-square test. -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __

Re: [R] a question about "latex" in Hmisc

ile for your table you can continue to use your original method, e.g., <<>>= tmp<- latex(x, file="x.tex") @ \include{x.tex} (not sure what your objection to this was in the first place). -Ista -- Frank E Harrell Jr Professor and ChairmanSchool of Medicin

Re: [R] P values

thz.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 ChairmanSchool of Medicine Depart

Re: [R] a matter of etiquette

what else? I only rule out writing (again) to the maintainers of the package. Adelchi Azzalini -- Adelchi Azzalini Dipart.Scienze Statistiche, Università di Padova, Italia tel. +39 049 8274147, http://azzalini.stat.unipd.it/ -- Frank E Harrell Jr Professor and ChairmanSchool of

Re: [R] How to estimate whether overfitting?

or 50-fold repeats of 10-fold cross-validation. Among other places these are implemented in my rms package. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University ___

Re: [R] How to estimate whether overfitting?

suggestion to improve model performance？ and is the picture bad? 5. the picture and data below. thank you! http://n4.nabble.com/file/n2164417/scatter.jpg scatter.jpg http://n4.nabble.com/file/n2164417/pkc-svm.txt pkc-svm.txt -- -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine

Re: [R] help on hmisc

neering Department of Applied mathematics, biometrics and process control Coupure Links 653 B-9000 Gent tel : +32 9 264 59 87 joris.m...@ugent.be --- Disclaimer : http://helpdesk.ugent.be/e-maildisclaimer.php [[alternative HTML version deleted]]

Re: [R] What is the best way to have "R" output tables in an MS

ad-to-head time-efficiency test many years ago of WYSIWYG word processing and markup languages by secretaries. The markup language approach won easily. This assumes that people don't mind learning things that take more than a day to learn. Frank --- On Thu, 5/6/10, Frank E Harrell Jr

Re: [R] sample size for survival curves

any suggestions. John As I recall, the survival probability used in Freedman is not at some arbitrary time of your choosing, but rather at the average length of follow-up time anticipated in the study. Kevin -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine

Re: [R] What is the best way to have "R" output tables in an MS

On 05/06/2010 07:28 PM, (Ted Harding) wrote: On 06-May-10 23:44:50, Frank E Harrell Jr wrote: Ted I can't resist offering my $.02, which is that I'm puzzled why LaTeX, being free, flexible, and powerful, is used only by millions of people and not tens of millions. Frank I think, F

Re: [R] What is the best way to have "R" output tables in an MS

Ted I can't resist offering my $.02, which is that I'm puzzled why LaTeX, being free, flexible, and powerful, is used only by millions of people and not tens of millions. Frank On 05/06/2010 03:07 PM, (Ted Harding) wrote: Replying to Chris's latest message for the sake of preserving the thre

Re: [R] Error messages with psm and not cph in Hmisc

ld and Adolescent Psychiatry [[alternative HTML version deleted]] __ 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] Latex and Stangle()

e Londrina Fone: 3371-4346 __ 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] Re : Re : aregImpute (Hmisc package) : error in matxv(X, xcof)...

an/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 ChairmanSchool of Medicine Department of Biostatistics Vanderbilt Uni

Re: [R] Visualizing binary response data?

help would be greatly appreciated, thanks, Kim -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org mailing list https://stat.ethz.ch/

Re: [R] Need help on having multiple distributions in one graph

ich is really quite simple in applications such as Stata. Thanks very much for the assistance: Joseph Hilbe hi...@asu.edu or jhi...@aol.com -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University ___

Re: [R] aregImpute (Hmisc package) : error in matxv(X, xcof)...

if these messages reflect a specific problem in my dataset ? And if the number mentioned might give me a hint on which column to look at (and maybe transform or ignore for the imputation) ? Thanks for any advice you might have. Marc [[alternative HTML version deleted]] -- Frank E Harrell Jr

Re: [R] What is the best way to have "R" output tables in an MS Word format?

in the core is a bit incongruent with having even provided tabs for matrices and tables? I'll pick up more in response to Max Kuhn's message. Very best, Chris -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Departmen

Re: [R] What is the best way to have "R" output tables in an MS Word format?

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 ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __

Re: [R] What is the best way to have "R" output tables in an MS Word format?

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. See http://biostat.mc.vanderbilt.edu/SweaveConvert -- Frank E Harrell Jr Professor

Re: [R] Robust ANOVA functions in R?

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 ChairmanSchool of Medicine Department of Biostati

Re: [R] Practical work with logistic regression

_ 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 ChairmanSchool of Medicine

Re: [R] Results from clogit out of range?

01-04_1 0 0.5260032 -2.977887 -0.02393871 By default (which is what you have implicitly chosen) you are requesting "lp" = linear predictors rather than "risk". Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversi

Re: [R] Help: coxph() in {survival} package

he multiple models and to get bootstrap confidence intervals for the ranks. I provided some code for this a couple of weeks ago. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostat

Re: [R] Serverless databases in R

x27;t it odd that the open-source R community has developed functions for reading in proprietary SAS and SPSS format files, but (AFAIK) the commercial sector doesn't seem to support reading data from open-sourced and open-specced R .Rdata files? Barry Hi Barry, Stat Transfer can read and write

Re: [R] problem with FUN in Hmisc::summarize

formula functions, or use tapply using a vector of possible subscripts (1:n) as the first argument; then you can use the subscripts selected to address multiple variables. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of B

Re: [R] Regression w/ interactions

r providing the right answer. Frank On Thu, Apr 15, 2010 at 8:26 AM, Frank E Harrell Jr mailto:f.harr...@vanderbilt.edu>> wrote: Michael Dykes wrote: I have a project due in my Linear Regression class re: regression on a data set & my professor gave us

Re: [R] Regression w/ interactions

th low signal to noise ratios. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/lis

Re: [R] Brier's score for bootstrap sample (coxph)

ible but will be noisy. You did not point to a function or package that claims to be able to compute a Brier score with censored data. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt Un

Re: [R] How to get the penalty matrix for natural cubic spline?

pline. Thanks a lot! Lee In usual practice the natural cubic spline does not use penalization. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __

Re: [R] Overfitting/Calibration plots (Statistics question)

t;- coef(lsfit(predict(lm2, d[101:200, ]), d$y[101:200]))[2] } mean(slope1) mean(slope2) I get > [1] 0.8873878 > [1] 0.9603158 Frank __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting

Re: [R] C-index and Cox model

C-index statistic to measure the predictive power, is it a time-dependent value (i.e. do I need to calculate it for each time period?) or we can calculate it as a single value for the whole model ignoring the time? Thank you so much. Bessy install.packages('Hmisc') ?rcorr.cens

Re: [R] glmpath in R

d these methods. Cheers, Claire __ 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] SAS and R on multiple operating systems

bg="transparent", width=700, height=500) example(forest) dev.off() Also I have seen 5,000 page listings in SAS. -- Frank E Harrell Jr Professor and ChairmanSch

Re: [R] sample size > 20K? Was: fitness of regression tree: how to measure???

ostatistics -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of Frank E Harrell Jr Sent: Thursday, April 01, 2010 5:02 AM To: vibha patel Cc: r-help@r-project.org Subject: Re: [R] fitness of regression tree: how to measure??? v

Re: [R] fitness of regression tree: how to measure???

data and that the form of the tree will not replicate in future datasets. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-projec

Re: [R] Problem comparing hazard ratios

th(rownames(x))) as.factor(rownames(x)) else as.factor(1:nrow(x)) cand <- reorder.factor(cand, x[,1]) Dotplot(cand ~ Cbind(x), pch=16, xlab='Rank', ylab='Candidate') } require(rms) n <- 100 age <- rnorm(n, 50, 10) sex <- sample(c('female',&#x

Re: [R] Problem comparing hazard ratios

-boun...@r-project.org] On Behalf Of Frank E Harrell Jr Sent: Tuesday, March 30, 2010 3:57 PM To: Michal Figurski Cc: r-help@r-project.org Subject: Re: [R] Problem comparing hazard ratios Michal Figurski wrote: Dear R-Helpers, I am a novice in survival analysis. I have the following code: for (i in 3

Re: [R] Problem comparing hazard ratios

likelihood ratio chi-square statistics of the competing biomarkers. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org mailing list

Re: [R] Paik, et al., NEJM, 2004, Fig. 4, rate of event at 10 years as a function of covariate

h(Surv(rtime, event) ~ rcs(covariate,4) + sex + ..., x=TRUE, y=TRUE) # restricted cubic spline with 4 knots plot(Predict(f, covariate, sex, time=10)) # separate curves for male and female; omit sex to make one curve; add age=50 to predict for a 50 year old -- Frank E Harrell Jr Professor and

Re: [R] how to measure accuracy of regression tree?

provide commented, minimal, self-contained, reproducible code. -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org mailing li

Re: [R] I have a question on nomograms.

Gabor Grothendieck wrote: On Thu, Mar 25, 2010 at 10:43 PM, Frank E Harrell Jr wrote: (Ted Harding) wrote: http://www.nomogram.org They call this sort of interface "nomogram" too, and you can have a go at the one they offer for bladder cancer. This is not a graphical nomogram in

Re: [R] I have a question on nomograms.

lues. So I can't suggest general-purpose nomogram generating software (and I doubt it would work well in many cases). Ted. E-Mail: (Ted Harding) Fax-to-email: +44 (0)870 094 0861 Date: 25-Mar-10 -- Fran

Re: [R] I have a question on nomograms.

e type of regression modeling used to produce a reliable model that is then displayed in a nomogram. The nomogram is the easy part; it is just a graphical display of a model. It is not the model itself. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine

Re: [R] ordinal regression

...@manchester.ac.uk -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do re

Re: [R] Find a rectangle of maximal area

mx1, mx1), c(my1, my1, my2, my2, my1), col=2) __ 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,

Re: [R] summary.formula and continuous variables

a Spearman correlation coefficient. Anyone wanting to work on the code should get the master code from our subversion repository. Frank -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University

Re: [R] How good is R at making publication quality tables?

rfect gift? Give the gift of Flickr! [[alternative HTML version deleted]] -- Frank E Harrell Jr Professor and ChairmanSchool of Medicine Department of Biostatistics Vanderbilt University __ R-help@r-project.or

Re: [R] logistic model diagnostics residuals.lrm {design}, residuals()

__ 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 Chairman

Re: [R] Cox Calibration regression test & double graphs

questions. B) Calibration plots are very easy for either logistic regression or Cox models when using the calibrate function in either Harrell's rms or Design packages. (Not sure about how well they play with survfit objects, but you ought to be able to apply the same methods.) -- Frank E Ha

Re: [R] Robust SE for lrm object

ut as I said above I'm not sure whether it would be very useful. Z Excellent posts. I'll just add that the Huber-White sandwhich estimator is obtain in the rms and Design packages by using the robcov function on a fit object. You can also use the bootstrap with bootcov. Frank -- Davi

  1   2   3   4   5   6   7   >