Joachim, sigma is the estimator of the standard error of the residual in the
regression equation. Also, 'rho' is not the estimated coefficient of the
inverse mills ratio (IMR) as you mentioned in your initial post. 'rho' is
the correlation coefficient of the error terms from the selection and the
regression equation. The coefficient of IMR is lambda and can be obtained by
multiplying rho with sigma. As an aside, if you're not using the -twostep-
option there is no point of talking about IMR's coefficient since there is
no such variable in your regression equation; rather ρ and σ are directly
estimated and lambda is just calculated by their multiplication.
P.S: I think Christophe is right that it should be u1~N(0,sigma^2) and NOT
u1~N(0,sigma) in the manual, could someone clarify that?
Hope this helps,
_____________ - _______________
Achilleas Vassilopoulos
Agricultural University of Athens,
Dept. of Agricultural Economics and Rural Development,
Lab. of Political Economy and European Integration.
Iera Odos 75, 11855, Athens, Greece
Tel: (+30) 210-5294726
Fax: (+30) 2105294786
e-mail : avassilopoulos.aua@gmail.com
-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of joachim jarreau
Sent: Friday, July 29, 2011 12:29 PM
To: statalist@hsphsun2.harvard.edu
Subject: st: statistics in heckman
Hello,
could anyone please explain to me what the 'sigma' is in results of
the heckman procedure? (It's actually lnsigma which is reported).
'rho' is the estimated coefficient on the inverse mills ratio, ok.
But I could not gather what sigma is, there is nothing with this name
in my textbook, section on the heckit.
The standard error on rho?
Thank you in advance,
joachim
*
* 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/
