Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: AW: Popularity of R, SAS, SPSS, Stata...


From   Neil Shephard <nshephard@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: AW: Popularity of R, SAS, SPSS, Stata...
Date   Fri, 25 Jun 2010 12:41:57 +0000

On Thu, Jun 24, 2010 at 5:37 PM, Nick Winter <nwinter@virginia.edu> wrote:
> At the risk of provoking flames - can someone articulate the reason *for*
> citing the statistical software used in a book or article, especially in the
> case where only very standard statistical tools are used?  We don't, for
> example, generally cite the word processor, citation management software,
> and other computer tools used in the course of our research....
>

There are issues of software validation too when it comes to clinical
trials.  If you didn't cite what software and version you had used no
one else would be able to replicate exactly your analysis.

Its all part of reproducible research to my mind.  People in
laboratories would keep meticulous lab books detailing reagents, PCR
amplifications, and genotyping platforms and these would then be cited
when the work is written up, yet once they had obtained their data
they'd manage it in Excel which has no way of recording data
manipulations and do some ad-hoc analysis and write up the results.
Given the strange behaviour of Excel when it comes to statistics (see
Allstat post at
https://www.jiscmail.ac.uk/cgi-bin/wa.exe?A2=ind01&L=allstat&P=R31997
Nick Cox's response is quite pertinent) its right to expect people to
question what software has been used, just as you need to know the
methods and tools used for any other aspect of the research.

The following article compares the accuracy of a number of different
stats packages

Kellie B. Keeling and Robert J. Pavur, A comparative study of the
reliability of nine statistical software packages. Computational
Statistics & Data Analysis 51:3811-3831

...and there is variation in performance, so knowing which has been
used is important.

For user-written programs there is the additional facet that it gives
credit where credit is due and may allow the developer of the program
to secure further funding to develop programs further if they can
demonstrate that their work and programs to date have been useful in
the wider community.

Neil


-- 
"... no scientific worker has a fixed level of significance at which
from year to year, and in all circumstances, he rejects hypotheses; he
rather gives his mind to each particular case in the light of his
evidence and his ideas." - Sir Ronald A. Fisher (1956)

Email - nshephard@gmail.com
Website - http://slack.ser.man.ac.uk/
Photos - http://www.flickr.com/photos/slackline/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index