similar to: Barnard's sequential t-test code ?

[my original message to s-news & r-help is attached ] No one possessed or knew of any S/R code for the sequential t-test. Also it doesn't appear in the SAS index. One or two suggested obtaining the S+ seqtrial software which may (or may not) cover this, but this seemed to be a bit of a "hammer to crack a nut". I have written a function based on the treatment in Wetheril

hi Andrew Many thanks for the suggestion. I gave it a try , but still get the same issue - a fresh Rgui window (just one) opens, with an empty .RData, when I submit a script ( Ctrl & F8 ). I also tried running things as administrator, but it made no difference. Apparently windows 7 is selling like hot buns, so there should be enough market pressure before too long , to encourage the

The original question is attached at the end of this message ... In the world of R the excellent mvtnorm package answers my original question and many more that I didn't know I needed to ask. In the world of Splus ( version 6 , Windows XP ) this link :- http://www.biostat.wustl.edu/archives/html/s-news/2002-11/msg00079.html which was provided by Dimitris Rizopoulos, is useful.

something like ... > x<-c(1,2,3,0,5,6,0) > is.na(x[x==0])<-T > x [1] 1 2 3 NA 5 6 NA ~~~~~~~~~~~~~~~~ Robert Kinley ~~~~~~~~~~~~~~~~ [[alternative HTML version deleted]]

We (Eli Lilly & co) have a vacancy for an experienced industrial statistician who is familiar with mainstream statistical software, particularly Splus (or R) and/or SAS and/or JMP. The role is to provide expertise and training in Statistics in support of process-improvement in all areas of the business, particularly Statistical Process Control, Design of Experiments, and Quality

Eli Lilly and company is one of the world's leading research-based pharmaceutical companies, and Lilly UK is one of the "Sunday Times Top 100 Best Companies To Work For". Due to growth, a new opportunity has arisen for an experienced Statistician with excellent communication skills to join our European team providing expertise and training in statistics to support pharmaceutical

Eli Lilly and company is one of the world's leading research-based pharmaceutical companies, and Lilly UK is one of the "Sunday Times Top 100 Best Companies To Work For". Due to growth, a new opportunity has arisen for an experienced Statistician with excellent communication skills to join our European team providing expertise and training in statistics to support pharmaceutical

I really like RStudio ... ... but I wish it wouldn't automatically reload the last .RData it had. Anyone know how to fix this ... ? Also - does anyone know is there an Rstudio-user email-list forum thingy out there ? ta. Robert Kinley [[alternative HTML version deleted]]

Hi For bureaucratic reasons beyond my control I need to rewrite an R function (for producing operating characteristic curves) as an Splus function ( version 6 , windows XP ). The R function makes extensive use of the fact that the student's t distribution function pt() has a non-centrality parameter built in ... sadly that parameter is not present in the Splus pt() function .

My small brain is having trouble getting to grips with lme() I wonder if anyone can help me correctly set the random = argument to lme() for this kind of setup with (I think) 9 variance/covariance components ... Study.1 Study.2 ... Study.10 Treatment.A: subject: 1 2 3 4 5 6 etc. 28 29 30 Treatment.B: subject: 31

Hello R help members. I came across today with an article on Barnard's exact test (http://www.cytel.com/Papers/twobinomials.pdf), that is supposed to give a more powerful fisher.test - Because it doesn't assume that we know the row and column totals are in advance. Any pointers to such a function ? Thanks, Tal -- ---------------------------------------------- My contact information:

hi I've used R for many years on windows machines, but have now acquired an Asus eee 1000 linux machine. In order to get the best out of the machine, I used the 'pimpmyeee.sh' script, to get the full KDE desktop. The version of Linux is Xandros, which I believe is a close relative of Debian, but sadly I have only a nodding acquaintance with Linux at present. Naturally I want to

On RH 5.2, and I've previously compiled and installed 3.0.28a on this box. configure ran clean, but make fails with:- Compiling smbd/server.c Linking bin/smbd smbd/server.o: In function `housekeeping_fn': server.c:(.text+0x21e): undefined reference to `attempt_machine_password_change' collect2: ld returned 1 exit status make: *** [bin/smbd] Error 1 Anyone else encountered this?

It's often useful to view objects in time order. In Splus I can do this with > objects.summary(order = "dataset.date") which delivers this sort of thing ... data.class storage.mode extent object.size dataset.date reference data.frame list 25 x 4 1700 2004.09.13 15:43 x data.frame list 15 x 4 1175

I'm encountering some oddness using Samba 3.0.28a, MIT kerberos (1.6.3) for user authentication on Linux, to 2003 Active Directory. The password policy dictated by AD should lock accounts after 6 incorrect login attempts within a 30 minute period. However, it seems to halve that when logging in to these Linux boxes via ssh - so after 3 incorrect login attempts, the AD account gets locked.

Is there a way to have users of the samba server, but not add them by smbpasswd -a <UserID>? I want the samba server to be a domain member and the users to only authentic from the PDC. These are the steps that I have attempted: Users are in both the Windows domain and the UNIX NIS account 1. smbpasswd -j <Domain> -r PDC -U <admin> Joined the Domain 2. edited the

Is there a way to have users of the samba server, but not add them by smbpasswd -a <UserID>? I want the samba server to be a domain member and the users to only authentic from the PDC. These are the steps that I have attempted: Users are in both the Windows domain and the UNIX NIS account 1. smbpasswd -j AM -r PDC -U <admin> Joined the AM Domain 2. edited the smb.conf

Dear R--Help, My current research focuses upon sensitivity analyses which require [1] clusterings of patients in a baseline-covariate X space and [2] examining the distribution of within-cluster treatment differences in outcome. I have some primitive R code for this, but I want to be able to interact with graphical displays of within-cluster information (local average treatment effects) to

Dear R-devel, My current research focuses upon sensitivity analyses which require [1] clusterings of patients in a baseline covariate X-space and [2] examining the distribution of within-cluster treatment differences in outcome. I have generated some primitive R code for this, but I really need to be able to interact with graphical displays of within-cluster information (local average

> library(Kendall) > Kendall(1:3,1:3) WARNING: Error exit, tauk2. IFAULT = 12 <<<<<< tau = 1, 2-sided pvalue =1 I believe Kendall tau is well-defined for this case and the reported value is correct; isn't it a bug to give a warning? (And if, e.g., the pvalue is not well-defined in this case, wouldn't it be better to return NA or NaN or something?) Also,