st: User-written ml commands, svy, and predict

[Richard Williams <Richard.A.Williams.5@nd.edu>]

The -ml- command makes it very easy to add svy support for user-written 
routines.  You just have to add the option to your syntax.  So, when 
writing my own program, even though I have never used svy, I sort of 
figure, why not?

However, I am also adding -predict- support for my program.  So, here is 
where my question comes in.  Will the -predict- command need to do anything 
special given that estimates were generated using -svy-?  My program will 
probably have the same predict options as mlogit (partly because I am 
modifying mlogit_p to work with my program):

p, xb, stdp, stddp

I am mainly wondering about stdp and stddp.  I never use those myself, but 
I assume somebody does, so I want to make sure my calculation is 
correct.  If I am not sure of the calculation, I may just drop those as 
options.

So in short, does the fact that I am using svy change how things should be 
calculated in post-estimation commands in general, and for stdp and stddp 
in particular?  Or does the fact that svy has already affected the 
estimates for e(b) and e(V) mean that no further adjustment is needing when 
doing subsequent calculations?



-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX:    (574)288-4373
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW (personal):    http://www.nd.edu/~rwilliam
WWW (department):    http://www.nd.edu/~soc

*
*   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/