[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: Royston's mvis ado and version questions
At 09:21 PM 9/28/2004 -0400, Dave Purcell wrote:
Stata recommends that you specify the version of Stata you are using at the
top of programs and do-files that you write. Hence, somewhere early on in
an ado file you'll see a line like
A few questions:
1) I just installed Patrick Royston's mvis ado (and related files) and
tried to run it, but I'm getting a "version 8 not supported" error. Is
it safe to assume I can't use this with the version 7 I'm running (Born
08 Aug 2001)?
3) Is there a way to tell if an ado file requires a certain version?
I've looked through the FAQs and haven't come across an answer.
Try to run that program in an earlier version of Stata and you'll get
errors like you saw.
Now, it is always possible that the program would work fine with an earlier
version of Stata. So, you could try making a copy, changing the version to
7, and see what happens. But, keep in mind that (a) it may not work at
all, because it requires version 8 features, and (b) worse still, it may
seem to work but give the wrong answers. The author will typically only
have tested it with the version of Stata they happen to have, so there are
no guarantees if you try it with a lower level version.
So, I suppose you could try to hack the programs; but if you did, I'd
suggest making sure you run them on problems with known results to see if
it seemed to be working correctly. I don't know anything about -mvis- but
I see that it deals with missing data, so one immediate concern I would
have is whether it is dependent on the changes in MD that were made in
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
* For searches and help try: