Statalist The Stata Listserver

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

RE: st: RE: Frontier,stata 8 & stata 9

From   "Gauri Khanna" <>
Subject   RE: st: RE: Frontier,stata 8 & stata 9
Date   Sat, 10 Jun 2006 06:28:14 +0000

Dear Scott,

I did try the difficult option but that too had failed. I also looked at the gradient to see whether it nears zero and it does... so I thought that might be a good point to stop the iteration if the gradient no longer changes or arbitrarily set iterations to a maximum of 500 and take the values at that point?

Regarding the maximisation algorithm, where can I find more information on this as I am not aware of this.

Also, I guess you would not know why the noconstant option is not working in stata 8 for the equation:
frontier logoutput logcorarea loglabour logmanure logfertiliserval logtrac logox logirrigation cropdum, uhet(experience age corarea, noconstant). I tried various combinations, eliminating the space or inserting brackets... but no show.

Thank you for your help.


From: "Scott Merryman" <>
To: <>
Subject: st: RE: Frontier,stata 8 & stata 9
Date: Fri, 9 Jun 2006 17:00:03 -0500

> -----Original Message-----
> From: [mailto:owner-
>] On Behalf Of Gauri Khanna
> Sent: Friday, June 09, 2006 4:57 AM
> To:
> Subject: st: Frontier,stata 8 & stata 9
> 2. I am also running into convergence problems with my frontier
> iterations.
> I decided to assign a lower tolerance level of ltolerance(1e-4) which
> works
> in stata SE8.1 but refuses to converge when I use stata 9 in the office.
> I
> tried 1e-7 for stata 9 but it did not work either in stata 9. Does anyone
> have a solution to the convergence problem in stata 9?

Have you tried using the difficult option or changing the maximization


* For searches and help try:
Express yourself instantly with MSN Messenger! Download today it's FREE!

* For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index