Mail Archive Search: <+from:arrayprofile@yahoo.com>

Results:

References: [ +from:arrayprofile@yahoo.com: 22 ]

Total 22 documents matching your query.

1. cph() in Design package (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Tue, 11 Apr 2006 11:11:03 -0700 (PDT); can; /archives/html/s-news/2006-04/msg00048.html (9,687 bytes)
2. setting missing value in a character matrix in S-Plus (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Thu, 17 Feb 2005 14:09:41 -0800 (PST); how can I set some elements in a character matrix as missing values (NAs)? for example: x<-matrix(rep('q',30),nrow=5) x[x=='q']<-NA will give me a character matrix with all elements being "NA", but; /archives/html/s-news/2005-02/msg00095.html (7,782 bytes)
3. sum of squares (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Fri, 25 Feb 2005 14:27:15 -0800 (PST); for balanced 2-way ANOVA, type I SS should be equal to Type III SS, this can be seen in the help page for summary.aov() as well. However, with the following simple example, I get different type I an; /archives/html/s-news/2005-02/msg00146.html (7,453 bytes)
4. Re: sum of squares (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Fri, 25 Feb 2005 15:09:59 -0800 (PST); Thanks. Yes, it is the same now. I just thought since values of a and b are coded either 0 or 1, so conceptually the model matrix should be the same whether a and b are factorized. And the model mat; /archives/html/s-news/2005-02/msg00148.html (10,537 bytes)
5. contrast reference level (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Thu, 2 Dec 2004 15:29:27 -0800 (PST); suppose I have a factor with 4 levels: 'a','b','c','d'. I would like to do analysis of variance using aov() with the factor as independent variable. How can I specify the level "b" as the reference l; /archives/html/s-news/2004-12/msg00014.html (7,507 bytes)
6. using Hmisc and Design library (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Tue, 14 Dec 2004 16:14:30 -0800 (PST); Hi, I encountered a weird problem when using the Design and Hmisc problem. I have 2 data frame called "a" and "b", both have 3 columns: "time", "status" and "scores", a sample of the data frame is li; /archives/html/s-news/2004-12/msg00096.html (8,890 bytes)
7. Re: using Hmisc and Design library (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Tue, 14 Dec 2004 16:27:33 -0800 (PST); actually data frame "b" has 177 rows, the script ran ok on the first 166 rows as a subset, but started to break down if subset of the first 177 rows were used as the dataset, or the first 166 rows pl; /archives/html/s-news/2004-12/msg00097.html (11,103 bytes)
8. Re: [R] Re: using Hmisc and Design library (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Tue, 14 Dec 2004 17:02:25 -0800 (PST); sorry, I had a typo there, it's datadist(b) for the analysis of data frame "b". -- __________________________________ Do you Yahoo!? Jazz up your holiday email with celebrity designs. Learn more. htt; /archives/html/s-news/2004-12/msg00098.html (13,740 bytes)
9. using Hmisc and Design library (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Wed, 15 Dec 2004 11:43:17 -0800 (PST); Hi all, I encountered a weird problem when using the Design and Hmisc libraries in S-Plus (it worked well in R). I have a data frame called "b", which has 3 columns: "time", "status" and "scores", a; /archives/html/s-news/2004-12/msg00106.html (17,044 bytes)
10. worked in R, but not in S-Plus (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Tue, 9 Nov 2004 16:50:09 -0800 (PST); I wrote a function that worked well in R, but not in S-Plus, can anyone suggest a solution? { cox.fit <- coxph(Surv(time.cox, status.cox) ~ x, na.action = na.exclude, method = "breslow") fit.zph<-co; /archives/html/s-news/2004-11/msg00069.html (7,914 bytes)
11. multinomial logistic regression (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Wed, 22 Sep 2004 17:36:49 -0700 (PDT); (almost as a s; /archives/html/s-news/2004-09/msg00122.html (6,657 bytes)
12. axis label character bolder (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Mon, 19 Apr 2004 11:16:43 -0700 (PDT); Hi, how can I, in S-Plus, make the character label of the axes of a plot darker (bolder), but not in a larger size? __________________________________ Do you Yahoo!? Yahoo! Photos: High-quality 4x6 d; /archives/html/s-news/2004-04/msg00093.html (6,499 bytes)
13. plot of survival probability vs. covariate (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Thu, 11 Dec 2003 15:23:37 -0800 (PST); Hi everyone, I am fitting a cox proportional hazard model with a continuous variable "x" as the covariate: fit<-coxph(Surv(time, status)~x) Now I wanted to make a plot of survival probability vs. the; /archives/html/s-news/2003-12/msg00069.html (7,635 bytes)
14. lme vs. aov with Error term (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Thu, 2 Oct 2003 09:42:21 -0700 (PDT); I have a question about using "lme" and "aov" for the following dataset. If I understand correctly, using "aov" with an Error term in the formula is equivalent to using "lme" with default settings,; /archives/html/s-news/2003-10/msg00020.html (10,709 bytes)
15. Re: lme vs. aov with Error term (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Thu, 2 Oct 2003 11:54:21 -0700 (PDT); Hi Bert, Thanks for the suggestions. I tried lme with different control parameters, and also tried using "ML", instaed of "REML", but still got the same answers. Yes, I hope some gurus on this list c; /archives/html/s-news/2003-10/msg00021.html (14,681 bytes)
16. Re: lme vs. aov with Error term (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Thu, 2 Oct 2003 12:55:29 -0700 (PDT); Thank you very much for the explanation! what about if I specify using "ML" instead of "REML" in the lme? I found that I still got different answers even I use "ML" in the lme call. And in any case,; /archives/html/s-news/2003-10/msg00022.html (10,136 bytes)
17. leave one out in s plus (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Thu, 14 Aug 2003 10:35:35 -0700 (PDT); Hi, can we do leave one out corss validation in s-plus? especially with the lda function in MASS? thanks __________________________________ Do you Yahoo!? Yahoo! SiteBuilder - Free, easy-to-use web s; /archives/html/s-news/2003-08/msg00078.html (6,397 bytes)
18. nls fitting inside a loop in S-Plus (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Thu, 21 Aug 2003 14:48:19 -0700 (PDT); I encountered a weird problem of fitting nls inside a loop, it works well in R, but not in S-plus. The code is: data1<-cbind(c(2.87,1.66,0.44,-0.78,-2.00,-3.21,-4.43,-5.65,2.87,1.66,0.44,-0.78,-2.00; /archives/html/s-news/2003-08/msg00125.html (8,020 bytes)
19. regexpr problem (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Thu, 28 Aug 2003 11:30:01 -0700 (PDT); I encountered a problem using "regexpr". The code works fine in R, but not in S-Plus: when run in R, it shows what I wanted (and it make sense as well): [1] 1 attr(,"match.length") [1] 4 but if I tr; /archives/html/s-news/2003-08/msg00174.html (6,929 bytes)
20. cox proportional hazards model coefficient (score: 1): Author: array chip <arrayprofile@yahoo.com>; Date: Thu, 31 Jul 2003 15:21:54 -0700 (PDT); (; /archives/html/s-news/2003-07/msg00219.html (6,731 bytes)

Current List: 1 - 20
Page: [1] [2]