Ed,
I don't know about most employers, but here is our situation. I work for
a VA research unit. We have maybe 10 or 12 data analysts. The DA's
overwhelmingly prefer SAS because we can both manage data and analyze it,
handling multiple datasets which can be very large. Dealing with a lot of
files (whether 4 or 40) simultaneously is very easy in SAS. The DAs know
SAS because the university here teaches biostats in it and some key local
businesses use it. I think SAS keeping prices low for academic
institutions is a very important marketing strategy for them.
Our VA unit is affiliated with a university (UM). We work with both PhDs
and MDs. The PhDs seem to have no opinion about stat packages but the MDs
tend to prefer Stata. Having begun learning Stata the past year, I can
see its charms --consistent and concise syntax, concise output, easy
updates, and technical support beyond comparison. Still, I am finding I
prefer SAS and am having a much harder time moving to Stata than I did
moving from OSIRIS, MIDAS, and SPSS, transitions I have made in the
(murky) past. Maybe it's that dataset issue, or maybe I am just getting
too old and rigid.
Our unit's interest in possibly migrating to Stata is largely financial;
the prices SAS charges government entities are outrageous, especially
compared to the university prices most of us are used to. A SAS feature
that appeals to some employers, according to a colleague who came from
Parke-Davis in the 90s, is SAS' extensive report capabilities. So,
perhaps the employers you are hearing about are not bothered by SAS' high
prices, don't have key decision-makers who prefer Stata, are used to
hiring DA's who trained in SAS, and/or want the reporting features.
Laurel
On Fri, 24 Jan 2003, Edwin Earl wrote:
> I read with particular interest all replies to the query "On choosing a
> stats package". I am curious to know how Stata does compare to Splus and
> SAS. Is true that SAS is the most required by employers?
>
> Ed.
>
*
* 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/
