Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: svy frontier

From   anju parthan <[email protected]>
To   [email protected]
Subject   Re: st: svy frontier
Date   Tue, 8 Mar 2005 15:58:37 -0800 (PST)

Hi Jose

I am new to Stata and I am not familiar with frontier.
However, I am using survey data and I ran into a
similar problem. Stata does not have svy commands for
zero-inflated poisson and zero-inflated negative
binomial regression models. 

Someone recommended me to run these models using
iweights and then use suest .,svy command to get the
survey estimates.

For example

zip absdays age00  gender2 ethrace2 ethrace3 ethrace4
[iweight=perwt00f ], inflate(age00 gender2 ethrace2
ethrace3 ethrace4 )exposure(refper) score(PO*)

suest ., svy

Hope this is helpful

--- Jose Valderrama <[email protected]> wrote:
> Hi everyone
> I am trying to run frontier in a sample of cotton
> producers.  As far as
> I know the frontier does not include any survey
> design in its process.
> Does anybody know if there is any alternative in
> order to include the
> survey design in this kind of estimations?  I was
> trying to weight the
> sample using the irregular weights, but the results
> are a bit weird, in
> fact a possible overestimation of the technical
> efficiency of cotton
> producers... Any suggestions?
> Thanks in advance
> Jose.
> *
> *   For searches and help try:
> *  
> *
> *

Anju Parthan, 
Doctoral Candidate, 
The University of Texas at Austin, PHAR-PHARMACY ADMIN 
Tel: (512) 459-4942; Fax: (512) 471-8762

Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index