st: RE: RE: RE: how can I pass a parameter to gengammareg

["Nick Cox" <n.j.cox@durham.ac.uk>]

This post appears to be saying that you are puzzled that a program
-wsim-, which you do not explain, sometimes does not work in the way you
expect. 

-wsim- I imagine to be a program of your own, as -findit- turns up no
reference. 

Just about the only diagnosis possible is that -wsim- must contain one
or more bugs. Using -set trace- might help you in debugging. 

As I explained to you on 8 March, running a program "manually" --
meaning it seems typing input values on the command line -- is itself of
no consequence. All a Stata program knows is what is supplied to it from
outside. It does not know quite what supplied those values, another
program or a user typing -- unless you called it in such a way that you
made explicit via an option that its arguments came from a command line,
but in that case you would not be asking this question. 

To get better advice, you may need to provide much more information. 

Nick 
n.j.cox@durham.ac.uk 

Matteo Richiardi

your reply is very informative. I do not understand, however, while if I
run
the program manually, say by typing 

wsim .01
return list

I get the correct scalar 'diff', that is the estimated coefficient minus
.5.

-- 
View this message in context:
http://n2.nabble.com/RE-how-can-I-pass-a-parameter-to-gengammareg-tp4712
256p4722834.html

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/