Search String: Display: Description: Sort:

Results:

References: [ +from:andy_liaw@merck.com: 177 ]

Total 177 documents matching your query.

1. Re: a simple Friday question (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Fri, 24 Mar 2006 20:15:23 -0500
v
/archives/html/s-news/2006-03/msg00077.html (8,582 bytes)

2. Re: multivariate test for homogeneity of variances (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Thu, 16 Feb 2006 07:43:26 -0500
See if this helps: http://finzi.psych.upenn.edu/R/Rhelp02a/archive/33330.html Have no idea if it works w/o change in S-PLUS though. Andy -- Notice: This e-mail message, together with any attachments,
/archives/html/s-news/2006-02/msg00049.html (8,818 bytes)

3. Re: Linear regression model for data larger than the memory (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Wed, 25 Jan 2006 12:36:47 -0500
I guess the simplest approach is to read the data in pieces, and accumulate the SSCP matrix. Then use the Cholesky decomposition to get the estimates. You're quite literally doing the regression `by
/archives/html/s-news/2006-01/msg00081.html (8,842 bytes)

4. Re: rock in nnet (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Thu, 4 Aug 2005 13:28:54 -0400
r
/archives/html/s-news/2005-08/msg00016.html (8,907 bytes)

5. Re: Concerns about SPLUS version 7 (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Wed, 13 Jul 2005 00:08:30 -0400
I'll chip in my $0.02: 1. I find Insightful's marketing blurb for the big data library in the Enterprise Developer version a bit puzzling: I just check the price of a dual Opteron 275 server with 8GB
/archives/html/s-news/2005-07/msg00081.html (18,626 bytes)

6. Re: question on lists (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Wed, 11 May 2005 13:08:30 -0400
c
/archives/html/s-news/2005-05/msg00048.html (8,389 bytes)

7. Re: last question of the week (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Wed, 11 May 2005 20:04:14 -0400
a
/archives/html/s-news/2005-05/msg00060.html (18,690 bytes)

8. Re: tricky element pulling question (score: 1)
Author: .com>
Date: Thu, 7 Apr 2005 13:53:15 -0400
ers. So, if there
/archives/html/s-news/2005-04/msg00043.html (14,976 bytes)

9. Re: Anderson-Darling Test Statistic (score: 1)
Author: .com>
Date: Mon, 11 Apr 2005 14:04:00 -0400
nobody has that t
/archives/html/s-news/2005-04/msg00065.html (9,157 bytes)

10. Re: friend of mine's question (score: 1)
Author: .com>
Date: Sun, 24 Apr 2005 13:55:41 -0400
But within each c
/archives/html/s-news/2005-04/msg00147.html (11,537 bytes)

11. Re: matrix const. (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Tue, 1 Mar 2005 15:54:59 -0500
Assuming the data is in a data frame, and the `year' and `idcode' are of type `character', the following works in R: 8025 0987 1980 0.9880 0.9880 1981 0.9877 0.9877 1982 0.8766 0.8766 Andy -- Notice:
/archives/html/s-news/2005-03/msg00008.html (8,616 bytes)

12. Re: some questions about tree growing (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Tue, 8 Mar 2005 11:24:19 -0500
Class labels are not the only thing produced by the tree: It also outputs estimated class probabilities. Those `0' terminal nodes probably all have different estimated probabilities. Andy -- Notice:
/archives/html/s-news/2005-03/msg00031.html (9,326 bytes)

13. Re: load only a function from a library (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Wed, 23 Mar 2005 08:49:53 -0500
Perhaps slightly simpler: library(Design) rcs <- rcs rcspline.eval <- rcspline.eval detach() Andy -- Notice: This e-mail message, together with any attachments, contains information of Merck & Co.,
/archives/html/s-news/2005-03/msg00117.html (9,834 bytes)

14. Re: How to change a data structure? (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Mon, 7 Feb 2005 09:46:20 -0500
One trick is to use `index' as the row indices, and generate column indices, then use both: mytest2 <- function() { m <- 3 n <- 4 rindex <- c(1,1,1,2,2,2,2,3,3) cindex <- unlist(lapply(table(rindex),
/archives/html/s-news/2005-02/msg00024.html (9,836 bytes)

15. Re: transforming 2D matrix to 4D array (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Wed, 16 Feb 2005 20:55:45 -0500
If your columns are already sorted in the right way, just make the matrix into an array and aperm() as needed. Here's an example: A1.B1.C1 A2.B1.C1 A1.B2.C1 A2.B2.C1 A1.B1.C2 A2.B1.C2 A1.B2.C2 A2.B2.
/archives/html/s-news/2005-02/msg00083.html (9,158 bytes)

16. Re: sum of squares (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Fri, 25 Feb 2005 17:34:46 -0500
You need to make `a' and `b' factors. Andy -- Notice: This e-mail message, together with any attachments, contains information of Merck & Co., Inc. (One Merck Drive, Whitehouse Station, New Jersey, U
/archives/html/s-news/2005-02/msg00147.html (8,575 bytes)

17. Re: linear regression with or without intercept (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Sat, 1 Jan 2005 10:07:17 -0500
you elaborate on what part(s) of the output that are so different beyond your reasonable explanation? You fitted two conceptually very different models. Why would you expect the result to be similar
/archives/html/s-news/2005-01/msg00001.html (11,697 bytes)

18. Re: Splus book on Artificial Neural Network (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Mon, 3 Jan 2005 20:19:12 -0500
I suppose by nnet() you meant the function in the MASS library. If so, that's support software for the book `MASS', which contains discussion and examples. Have you tried that? (Google is a very usef
/archives/html/s-news/2005-01/msg00009.html (9,687 bytes)

19. Re: Dr. Bill Venables's Exegesis (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Fri, 7 Jan 2005 14:30:17 -0500
Is this the link you tried? http://www.stats.ox.ac.uk/pub/MASS3/Exegeses.pdf Andy Hello S+ users, Also, i was viewing the help file for 'multicomp' to perform some post-hoc comparisons for a nlme ana
/archives/html/s-news/2005-01/msg00041.html (8,507 bytes)

20. Re: Force a split in Rpart3 (score: 1)
Author: "Liaw, Andy" <andy_liaw@merck.com>
Date: Tue, 18 Jan 2005 15:17:01 -0500
f
/archives/html/s-news/2005-01/msg00087.html (8,280 bytes)


This search system is powered by Namazu