[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st:Hang Up
on 17/05/2004 20:18, Syed Gillani at email@example.com wrote:
> Hello all,
> Stata consistently hangs up on tabulate for two variables, both with more
> than two categories, with option exact.
> Is it just my system?
> Version = 8,2
> OS = Windows98 & WindowsXP Professional
Cannot replicate this on OS X, but note that the exact option has a heavy
overhead on processor time. While a 3 x 3 table with 121 obs took 3 seconds
(and that's a long time in Stata) a table with 1657 obs was still running at
400 seconds, at which point I aborted it. But Stata hadn't hung - it
responded instantly to <cmd-period> and duly reported the time taken.
Actually, hypothesis tests for tables that go beyond 2 x 2 are rarely
informative. Have you considered a more hypothesis-driven approach?
Ronan M Conroy (firstname.lastname@example.org)
Lecturer in Biostatistics
Royal College of Surgeons
Dublin 2, Ireland
+353 1 402 2431 (fax 2764)
Just say no to drug reps
* For searches and help try:
- st:Hang Up
- From: "Syed Gillani" <email@example.com>