Thanks scott!
I tried a different specification - not in first
differencing:
xtfrontier lnY/L lnK/L Foreign_dmy, tvd
Still for large number of sectors (16 out of total
26), the model is not coverging.
I tried using xtpcse command to get initial values.
Still it is not converging.
Any further suggestion!
Thanks!
Vinish
--- Scott Merryman <[email protected]> wrote:
> I don't think your specification is appropriate for
> a stochastic
> frontier model. If you wish to control for firm
> specific effects use
> -frontier- with firm dummy variables rather than
> first differencing.
>
> Scott
>
>
> On 7/12/07, vinish kathuria <[email protected]>
> wrote:
> > Thanks Scott!
> >
> > If I don't suppress constant term, for few it
> > converges but for few it still shows - not
> concave.
> >
> > However, the model also requires suppressing
> constant
> > term - as it is in difference!
> >
> > Vinish
> >
> *
> * 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/
>
Why delete messages? Unlimited storage is just a click away. Go to http://help.yahoo.com/l/in/yahoo/mail/yahoomail/tools/tools-08.html
*
* 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/
