Mail Archive Search: <+from:cberry@tajo.ucsd.edu>

Results:

References: [ +from:cberry@tajo.ucsd.edu: 14 ]

Total 14 documents matching your query.

1. s (score: 1): Author: <cberry@tajo.ucsd.edu>; Date: Thu, 8 Jan 2004 16:39:32 -0800 (PST); I Google'd Nightingale graph rose and this was the first hit: www.stats.bris.ac.uk/~magka/SFS/Unit1.pdf These appear to be course notes by Dr. Graeme Ambler. They show a rose plot from Nightingale's; /archives/html/s-news/2004-01/msg00026.html (10,056 bytes)
2. Re: Linear Clustering (score: 1): Author: <cberry@tajo.ucsd.edu>; Date: Thu, 2 Oct 2003 15:33:51 -0700 (PDT); Fisher describes several problems in that paper. I believe the 'unrestricted' clustering problem can be dealt with by 'rpart' along these lines Of course, this is not necessarily the optimal partiti; /archives/html/s-news/2003-10/msg00026.html (10,954 bytes)
3. Re: Truncated Exponential RNG (score: 1): Author: "Charles C. Berry" <cberry@tajo.ucsd.edu>; Date: Wed, 2 Jan 2002 17:50:38 -0800 (PST); By truncated exponential, if you mean f(x) = lambda * exp(-lambda * x)/ (1 - exp( -lambda *x ) ) for 0 <= x < 5 and 0 otherwise, rexp(n.desired,lambda) %% 5.0 # use memoryless property to advantage; /archives/html/s-news/2002-01/msg00014.html (8,982 bytes)
4. Re: Truncated Exponential RNG (score: 1): Author: "Charles C. Berry" <cberry@tajo.ucsd.edu>; Date: Wed, 2 Jan 2002 17:53:42 -0800 (PST); erratum on my previous email: --|||||||||||||||||||||||| should have been (1 - exp( -lambda * 5.0 ) ) Charles C. Berry (858) 534-2098 Dept of Family/Preventive Medicine E mailto:cberry@tajo.ucsd.edu; /archives/html/s-news/2002-01/msg00015.html (10,021 bytes)
5. Re: Confidence Interval on Quotient (score: 1): Author: "Charles C. Berry" <cberry@tajo.ucsd.edu>; Date: Tue, 30 Jan 2001 11:02:23 -0800 (PST); Try the classical interval for the ratio of means of Gaussian data: Fieller, EC(1940) The biological standardization of Insulin, Suppl to J.R.Statist.Soc, 7,1-64. Charles C. Berry (858) 534-2098 Dept; /archives/html/s-news/2001-01/msg00226.html (8,708 bytes)
6. Re: [S] Breslow Day Statistic (score: 1): Author: "Charles C. Berry" <cberry@tajo.ucsd.edu>; Date: Wed, 2 Aug 2000 10:38:12 -0700 (PDT); Hopefully, the answer to the question is NO. ("Has anybody written a function to calculate the Breslow-Day statistic?") As Norman Breslow took pains to point out in his plenary address ('The R.A. Fis; /archives/html/s-news/2000-08/msg00019.html (9,780 bytes)
7. Re: [S] significant digits bug in Splus 5.1 (score: 1): Author: "Charles C. Berry" <cberry@tajo.ucsd.edu>; Date: Wed, 22 Mar 2000 18:22:17 -0800 (PST); The problem Don describes below can be circumvented. [1] 1640 [1] 1600 [1] 2000 [1] 1637 [1] 1637 [1] 1637 I guess this might also be a hint as to the genesis of the problem. ?? Chuck Berry Charles C; /archives/html/s-news/2000-03/msg00204.html (10,943 bytes)
8. [S] multivariate regression routines ?? (score: 1): Author: "Charles C. Berry" <cberry@tajo.ucsd.edu>; Date: Tue, 22 Feb 2000 10:55:04 -0800 (PST); I need a hardy, fast regression solver for GENERAL multivariate linear regression setups. (By "GENERAL", I mean to include all of the linear regession cases mentioned in Box and Tsiao, 1973, viz. cas; /archives/html/s-news/2000-02/msg00207.html (8,474 bytes)
9. Re: [S] matrix (score: 1): Author: "Charles C. Berry" <cberry@tajo.ucsd.edu>; Date: Mon, 12 Apr 1999 10:47:53 -0700 (PDT); Here is a function that does what you want: "dbind"<- function(x) { len.x <- length(x) dim.x <- do.call("cbind", lapply(x, function(x) if (length(x) == 0) 0 else { if(length(x) == 1) c(1, 1) else di; /archives/html/s-news/1999-04/msg00097.html (10,377 bytes)
10. [S] Biostats Faculty Position Available (score: 1): Author: "Charles C. Berry" <cberry@tajo.ucsd.edu>; Date: Mon, 4 Jan 1999 10:19:43 -0800; Dear Colleagues; The University of California at San Diego has an open faculty position in biostatistics. I'd appreciate it if you could post the enclosed job announcement and/or pass it along to any; /archives/html/s-news/1999-01/msg00012.html (8,072 bytes)
11. RE: [S] Norm of a Gaussian r.v. (score: 1): Author: "Charles C. Berry" <cberry@tajo.ucsd.edu>; Date: Thu, 12 Nov 1998 10:10:30 -0800 (PST); Alan Genz's integration software can be found on his home page: http://www.sci.wsu.edu/math/faculty/genz/homepage The routines there are Fortran and C, and not too hard to adapt to call from Splus -; /archives/html/s-news/1998-11/msg00057.html (10,653 bytes)
12. [S] step functions ala persp() (score: 1): Author: "Charles C. Berry" <cberry@tajo.ucsd.edu>; Date: Thu, 11 Jun 1998 10:41:21 -0700; Does anyone have/know of a function to plot a bivariate step function as a persp() type plot or a wireframe TIA, -- Charles C. Berry (619) 534-2098 Dept of Family/Preventive Medicine E mailto:cberry@; /archives/html/s-news/1998-06/msg00073.html (7,219 bytes)
13. [S] Ad: Biostatistics Faculty Position (score: 1): Author: "Charles C. Berry" <cberry@tajo.ucsd.edu>; Date: Wed, 04 Mar 1998 13:33:55 -0800; The University of California at San Diego has an open faculty position in biostatistics. The ad copy follows: == Biostatistics Faculty Position The UCSD Cancer Center and the Department of Family and; /archives/html/s-news/1998-03/msg00060.html (7,905 bytes)
14. [S] reasonable p-values for Fisher exact's test - WAS strange ... (score: 1): Author: "Charles C. Berry" <cberry@tajo.ucsd.edu>; Date: Tue, 24 Mar 1998 16:38:18 -0800; Before this thread enters an infinite loop, a few observations: First, class(fisher.test(etc) ) == "htest" So, print.htest() will format the results of fisher.test(). This is done as follows cat("p-v; /archives/html/s-news/1998-03/msg00256.html (11,873 bytes)

Current List: 1 - 14
Page: [1]