Thanks to Kenneth Rice (of the BUGS team) and SH Heisterkamp for helpful I have made minor modifications to two functions shared by Kenneth Rice that export data in S-Plus (whether based on the S3 or
Does anyone have functions for sending data from the S4 engine (as in S-Plus 6 for Windows) to a file that can be read as input by WinBUGS 1.3? The following command, executed in S-Plus 6.0 for Wind
The American Statistical Association's Section for Statistics in Marketing is sponsoring its first annual award competition, offering two separate $2000 scholarships to students who best apply statis
Here 'ya go.... [,1] [,2] [,3] [1,] 1 2 3 [2,] 2 5 6 [3,] 3 6 9 -- This message was distributed by s-news@wubios.wustl.edu. To unsubscribe send e-mail to s-news-request@wubios.wustl.edu with the BOD
Oops! My solution doesn't work for matrices larger than my 3-by-3 test case, as kindly pointed out to me by Peter Perkins, who also offers a solution that does work.... -- This message was distribute
I use different subdirectories to separate Three other simple practices help a lot to manage the plenitude of objects associated with a given project: (1) I use a period as the starting character of
Here ya go-- mean(x[seq(cnt)]), x) [1] 0.4398589 0.1554544 0.3108189 0.1515887 -0.2307677 [1] 0.4398589 [1] 0.1515887 Terry Elrod -- Terry Elrod Assoc. Prof. of Marketing 3-23 Faculty of Business Uni
Since posting my summary, I received additional suggestions that do not involve eval or do.call, but instead fix up the value returned by the called function (au) from within the calling function (st
Here's a problem that sometimes arises in S-Plus: I have written an estimation method which creates its own class. The estimation is accomplished by a function au with arguments such as innerarg. It
My heartfelt thanks to Nick Ellis, Pierre Joyet and Prof. Brian D. Ripley for helpful solutions. Rather than list all solutions, I reprint in full Prof. Ripley's reply, which is definitive and most i
Alan Zaslavsky [zaslavsk@hcp.med.harvard.edu] reminds me that default arguments are evaluated in the local frame. And come to think of it, the examples I have seen of formal.argument.name == actual.n
My thanks to Prof. Brian Ripley [ripley@stats.ox.ac.uk], Don MacQueen [macq@llnl.gov] and Jens Oehlschlaegel [oehl@Psyres-Stuttgart.DE] for their private replies to my query. I provide Prof. Ripley's
My suggested fix to nlminb.control has no effect on the running of nlminb. A detailed examination of the nlminb code shows that the value of diff.g passed to nlminb from nlminb.control is not (no lon
Here's a question for the experts. A good answer would be very useful to many, I think. It's often useful to attach a data frame at the command level--accessing its variables becomes more convenient
THE ERROR: In S-Plus 4.0, release 3, the help file for nlminb.control states that a parameter diff.g may be set by the user, but setting this parameter within a call to nlminb generates the error: "E
Here are a few quick thoughts pertaining to your question. First, the log transformation is equivalent to lambda = 0 for the Box-Cox, which is not too different from lambda = 1/3 for the cube root. T
I seek advice on whether switching to Windows NT would be better for running long S-Plus 4.0 jobs concurrently with other programs. It's time for me to get a new PC. I've settled on a 300MH or better
Many thanks to those who responded to my query, which was: I seek advice on whether switching to Windows NT would be better for running long S-Plus 4.0 jobs concurrently with other programs. It's tim