st: standard errors poverty measurement Stata 10

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view

st: standard errors poverty measurement Stata 10

Stephen P. Jenkins

Date: Fri, 05 Dec 2008 16:05:50 +0100
From: [hidden email]
Subject: st: standard errors poverty measurement Stata 10

Dear Stata users,

is there a command to derive in Stata 10 with standard errors for  
Foster, Greer and Thorbecke type of poverty measurements?

The poverty rate a such I edrived as following (for one specifc

poverty  pcexp if region==1 , line(9500.4)  h

< snip >

Best regards



You could use -povdeco- and bootstrap (since you appear not to have
sample weights; they complicate the use of standard bootstrapping
methods -- see Stas Kolenikov's posts)

Alternatively, use linearised methods, exploiting the fact that almost
all poverty indices are means of a convenience variable that you can
easily create. This means that all the power of the -svy- commands can
be applied.

For examples, using Stata 8 I recall, see:

Jenkins, S.P. 2006. Estimation and interpretation of measures of
inequality, poverty, and social welfare using Stata. Presentation at
North American Stata Users' Group Meetings 2006, Boston MA.

[Users already familiar with this presentation might note that the zip
file containing materials has just been updated to contain 3 data
creation do files to explain how the data used in the presentation
examples were created.  Thanks to Kit Baum for updating the zip file
archive for me.]

Professor Stephen P. Jenkins <[hidden email]>
Director, Institute for Social and Economic Research
University of Essex, Colchester CO4 3SQ, U.K.
Tel: +44 1206 873374.  Fax: +44 1206 873151. 
Survival Analysis using Stata: 
Downloadable papers and software:

Learn about the UK's new household panel survey, "Understanding

*   For searches and help try: