Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: Re: st: Problems using predict in xtfrontier


From   "Dascha Orlova" <dascha.or@gmx.de>
To   statalist@hsphsun2.harvard.edu
Subject   Re: Re: st: Problems using predict in xtfrontier
Date   Wed, 29 Aug 2007 15:37:48 +0200

>Are you sure they should vary?  I don't have books with me but isn't
>eta summed over all the time periods (for each individual) for
>- -predict var, u- and predict var, m- making the predictions time
>invariant?
>Scott

Dear Scott,
thank you! You're right, the estimates for u really shouldn't vary if one examines the formula properly. :-)
But I still don't understand what sense time invariant u-estimates make in a time-variant model. For if I use any other way to calculate cost efficiency than -predict var, te- the efficiency won't vary with time because of the invariant u's. And if one considers the logic behind the model, the u's are the only cause of the time-variant efficiency scores...
SFA seems to be too intricate for me, sorry :-(


-- 
GMX FreeMail: 1 GB Postfach, 5 E-Mail-Adressen, 10 Free SMS.
Alle Infos und kostenlose Anmeldung: http://www.gmx.net/de/go/freemail
*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index