Search String: Display: Description: Sort:

Results:

References: [ +from:f.harrell@vanderbilt.edu: 85 ]

Total 85 documents matching your query.

1. Re: ROC curves in S? (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Thu, 08 Dec 2005 15:00:38 -0600
Thanks, Nicky Don't draw the curve, which can lead people to select arbitrary cutpoints on the predicted probabilties and to use an improper loss (utility) function. But the area under the ROC curve
/archives/html/s-news/2005-12/msg00024.html (9,059 bytes)

2. Re: ROC curves in S? (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Fri, 09 Dec 2005 10:57:45 -0500
I'll try to be as helpful as I can here and not confuse what is a relatively simple request on your part: I am not an S-Plus user but am aware of the many similarities between this and R. I do not pr
/archives/html/s-news/2005-12/msg00029.html (9,324 bytes)

3. Re: Any S-plus/R doc or manual for SAS user out there? (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Tue, 13 Sep 2005 11:40:07 -0500
I am looking for an Splus or R doc / manual for SAS user. Thank you in advance. PK Somewhat helpful in that regard: http://biostat.mc.vanderbilt.edu/twiki/pub/Main/RS/sintro.pdf -- Frank E Harrell Jr
/archives/html/s-news/2005-09/msg00034.html (8,160 bytes)

4. Re: Bootstrap CIs with log transformation (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Wed, 10 Aug 2005 08:21:58 -0400
&
/archives/html/s-news/2005-08/msg00039.html (9,734 bytes)

5. Re: SAS Programming Tip from SAS Certified Professional - Sunil (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Thu, 07 Jul 2005 12:09:38 -0500
I thought you might be interested in this tip I wrote for SAS. It is one of many useful techniques in my latest book, Sharpening Your SAS Skills, (www.crcpress.com). SAS Programming Tip from SAS Cert
/archives/html/s-news/2005-07/msg00032.html (9,112 bytes)

6. Re: SAS Programming Tip from SAS Certified Professional - Sunil (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Thu, 07 Jul 2005 12:43:23 -0500
Best, Janusz. This is based on a scientific formal analysis: I used SAS for 22 years and have used S-Plus/R for 14 years, looked at the quality of analyses done by SAS users, S-Plus/R users, and myse
/archives/html/s-news/2005-07/msg00033.html (11,278 bytes)

7. Re: Interface between R and Splus (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Mon, 11 Jul 2005 12:37:36 -0500
Hello, I am using currently the evrsion 6.1 of Splus. Does anyone know if there is a way to call R functions from Splus (interface...?). The function I Not in general want to use (download.file) is n
/archives/html/s-news/2005-07/msg00053.html (8,635 bytes)

8. Re: Concerns about SPLUS version 7 (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Tue, 12 Jul 2005 10:49:21 -0500
These are very serious problems. I did not realize the licensing changes for S-Plus 7. -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University
/archives/html/s-news/2005-07/msg00068.html (8,527 bytes)

9. Re: bubbleplot in a panelplot (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Tue, 12 Jul 2005 10:51:08 -0500
Karin wrote: Hello, I want to make bubbleplots in stead of an ordinary scattor plot in a panel plot. Does anyone know how to do this? What kind of panelfunction do I have to take? Thanks in advance,
/archives/html/s-news/2005-07/msg00069.html (8,354 bytes)

10. Re: Off-topic: Anocova of change scores with baseline (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Wed, 11 May 2005 04:44:39 -0500
a
/archives/html/s-news/2005-05/msg00044.html (9,326 bytes)

11. Re: statistical terminology controversy (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Wed, 18 May 2005 21:54:32 -0500
n
/archives/html/s-news/2005-05/msg00125.html (12,495 bytes)

12. (no answer) (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Fri, 01 Apr 2005 07:01:03 -0600
I wish to perform brain surgery this afternoon at 4pm and don't know where to start. My background is the history of great statistician sports legends but I am willing to learn. I know there are cour
/archives/html/s-news/2005-04/msg00000.html (7,563 bytes)

13. Re: something between multinom() and polr()/lrm() (score: 1)
Author: .edu>
Date: Tue, 26 Apr 2005 13:01:29 -0400
have a question (
/archives/html/s-news/2005-04/msg00156.html (10,491 bytes)

14. Re: load only a function from a library (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Wed, 23 Mar 2005 06:07:39 -0600
Dear List Members: I need to call a function (namely RCS) from the Design library (SP 2000), but this library seems to have troubles with GLM function. I don't know about obsolete versions, but in l
/archives/html/s-news/2005-03/msg00115.html (9,100 bytes)

15. Re: Trapezoidal method for AUC calculation (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Tue, 08 Feb 2005 08:51:18 -0600
Here a function: "AUC"<- function(time, y, na.rm = T) { if(na.rm == T) { sel.1 <- !is.na(time) sel.2 <- !is.na(y) sel <- sel.1 * sel.2 tt <- time[sel == 1] yy <- y[sel == 1] xxx <- sum((sort(tt) - tt
/archives/html/s-news/2005-02/msg00033.html (9,936 bytes)

16. Re: How to change a data structure? [Usefulness for clinical (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Tue, 08 Feb 2005 08:53:08 -0600
The Clinical Data Standards Interchange Committee (CDISC, www.cdisc.org ) has recently developed the Study Data Tabulation Model (SDTM) for data from pharmaceutical clinical trials. These tabulations
/archives/html/s-news/2005-02/msg00034.html (9,743 bytes)

17. Re: logistic regression - no R squared or F output in long format (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Thu, 24 Feb 2005 08:53:29 -0500
Hi all, Just wondering if anyone can help a beginner - having trouble getting an R squared output from logistic regression in splus 6.2 student version. I get Deviance Residuals, Min 1Q Median 3Q Max
/archives/html/s-news/2005-02/msg00122.html (9,600 bytes)

18. Re: logistic regression - no R squared or F output in long format (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Thu, 24 Feb 2005 09:28:09 -0500
But is occasionally still useful: @ARTICLE{cox92, author = {Cox, D. R. and Wermuth, N.}, year = 1992, title = {A comment on the coefficient of determination for binary responses}, journal = {The Amer
/archives/html/s-news/2005-02/msg00125.html (9,995 bytes)

19. Re: factor levels (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Fri, 25 Feb 2005 10:22:35 -0500
For example: coef exp(coef) se(coef) z p V151 3.263 26.136 24.427 0.1336 0.89 V152 1.004 2.729 8.149 0.1232 0.90 V153 0.227 1.255 4.080 0.0556 0.96 V154 0.136 1.146 2.452 0.0556 0.96 V155 -0.772 0.4
/archives/html/s-news/2005-02/msg00139.html (9,145 bytes)

20. Re: Plotting logistic curve with confidence limits (score: 1)
Author: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Sun, 02 Jan 2005 20:54:55 -0500
Thanks for any help. David Parkhurst One of several ways: library(Hmisc,T);library(Design,T) dd <- datadist(mydataframe); options(datadist='dd') f <- lrm(death ~ pol(age,2) + sex) # quadratic in age
/archives/html/s-news/2005-01/msg00003.html (8,122 bytes)


This search system is powered by Namazu