Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: heteroskedastic panel frontier

From   Manzur Quader <>
Subject   st: heteroskedastic panel frontier
Date   Wed, 9 Jun 2010 22:21:17 +0100


I am using stochastic frontier model to calculate agency cost of firms
using Tobin's Q as dependent variable.I have got data of 1200 firms
over 3 to 29 years.But,whenever I am using xtfrontier I am getting
very low efficiency level(below 40%,which is very low compared to the
literature) and this is probably due to heteroskedasticity.If I use
frontier on the pooled data or on different cross sections by year
conditional on uhet,I am getting much better result.

Can you please tell me is there any way to incorporate
heteroskedasticity if I want to use xtfrontier for my panel?I know
that the Battesse and Coelli(1995) model can be estimated in stata,but
is there any way I cam parameterize the mean efficiency in terms of z
simultaneously?Or is there anything like uhet for panel frontier?

Please advise.

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index