<>
There may be no LR test, but Stata does still provide you with a confidence
interval for -rho-. What do you read into this CI?
*************
webuse womenwk, clear
gen weights =int(10*runiform())
svyset _n [pweight=weights], /*
*/ vce(linearized) singleunit(missing)
svy linearized : heckman wage educ age, /*
*/ select(married children educ age)
*************
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Nefer Liliana
Olarte Rodriguez
Gesendet: Freitag, 30. Oktober 2009 09:05
An: [email protected]
Betreff: st: svy : heckman
Im working with survey data [pweights]. I used the svy : heckman command
for
correcting selectivity but i dont know if rho is statistically different
from zero.
I know LR test cannot be applied when using weights but i don't know how to
implement any other test (Wald Test for example).
Thanks for you attention,
Liliana Olarte
*
* 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/
*
* 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/