 |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: Correct code for Poi's QUAIDS model
On Fri, 2 May 2008, [email protected] wrote:
Hi,
Can somebody mail me the correct code for Poi's (2002) QUAIDS model. I
downloaded the code from http://www.stata-journal.com/software/sj2-4/st0029/
but I suspect there are some mistakes in this code as I keep getting error
message like 'conformability error' or 'the subcommand post has been moved
from estimates to ereturn' when I run the code. I would like to be able to
replicate his results to see how this works in Stata.
I have emailed Lavanya a zip file containing programs to fit a QUAIDS
model.
I have never had anyone report a conformability error when running my
QUAIDS code, though the error messages pertaining to the command
-estimates post- moving to -ereturn post- is understandable, since the
-estimates- commands were rewritten and renamed -ereturn- in Stata 8 or
Stata 9. For those who want replicate the steps I took in that Stata
Journal article, just change the commands -estimates post- and -estimates
display- to -ereturn post- and -ereturn display-, respectively.
Also, I'm using Stata 10 and the code for Poi's example was written in Stata
version 7 (all the .ado files say version 7).. could this cause a problem in
the code running properly in State version 10?
For those who have access to Stata 10, I strongly recommend using -nlsur-
instead of the programs in my 2002 Stata Journal article. The last
example in the reference manual entry for -nlsur- shows how to fit the
basic AIDS model, and it can be adapted to other demand systems as well.
Using -nlsur- requires just one program instead of the small handful that
the older method using -ml- requires, and -nlsur- tends to fit these
models much more quickly.
-- Brian Poi
-- [email protected]
*
* 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/