Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: do-file hygeine


From   Nick Cox <[email protected]>
To   [email protected]
Subject   Re: st: do-file hygeine
Date   Mon, 29 Sep 2008 14:02:14 -0500

Also perhaps (not yet seen by me, but I keep meaning to check it out)

M. Schwab, M. Karrenbach, and J. Claerbout, "Making scientific computations reproducible," Computing in Science & Engineering, vol. 2, no. 6, pp. 61--67, November-December 2000.


David Radwin wrote:

In my opinion, more fundamental than the mechanics of managing do-files is the philosophy that your work should be replicable by another researcher in the sense that if she were to use the same data and methods. In the specific case of Stata, that would ideally mean the same dataset, do-files, and programs could be used to create exactly the same results, including such niceties as using the -set seed- command, but the replication principle goes far beyond that.

A side benefit of this philosophy is that it may force you to be more explicit and thoughtful about your data analysis decisions.

For a nice discussion of replication in the social sciences, see Gary King, "Replication, Replication," PS: Political Science and Politics, followed by comments from nineteen authors and a response, Vol. XXVIII, No. 3 (September, 1995): pp. 443-499 and http://gking.harvard.edu/projects/repl.shtml .

David

At 11:08 AM -0700 9/27/08, Michael McCulloch wrote:

I'd appreciate any pointers toward good do-file hygeine, i.e. management practices to maximize good record keeping, with resulting least likelihood of overlooking important details.


*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index