st: tech report on strategic use of stat packages

[Kit Baum <baum@bc.edu>]

Michael writes
"7. It is penny wise and pound foolish to skimp on purchasing useful  
statistical software. Statistical
software can be one of the most powerful tools for testing your  
hypotheses and advancing your research.
Using an inappropriate tool to save a modest amount of money is more  
costly in terms of your time,
and more costly in terms of handicapping your ability to put forth  
the most compelling statistical case
possible. Consider the value of software by weighing its costs  
against the benefits it provides."

It is equally important to consider budgeting for updates to stat  
packages. With some packages, there are annual fees, so this is not  
an issue. But for Stata, many users' difficulties and anguished cries  
for help on Statalist are related to their use of older versions of  
Stata that do not possess the same suite of capabilities as the  
current version. Likewise, many user-written contributions require an  
up-to-date version of Stata, because user-programmers are making use  
of the enhancements.

Although it is often more difficult (in my experience) for an  
institution to deal with an infrequent (ca. every 2-2.5 years) and  
sizable update fee than it would be to budget an annual maintenance  
fee, users at those laggard institutions should be mobilized to press  
for updates when they become available. The additional features and  
speed improvements made accessible by Mata---even if you never write  
a line of Mata---alone are worth the upgrade to version 9.x.

Kit Baum, Boston College Economics
http://ideas.repec.org/e/pba1.html


*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/