Statalist


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

st: Microdata Adjustment through re-weighting


From   Andreas Peichl <peichl@iza.org>
To   statalist@hsphsun2.harvard.edu
Subject   st: Microdata Adjustment through re-weighting
Date   Fri, 15 May 2009 19:52:23 +0200

Dear statalister,

I'm interested in re-weighting a microdata sample to fit aggregate control
data based on the Minimum Information Loss (MIL) principle (see Merz 1994).
Based on information theory this principle satisfies the desired positivity
constraint on the weighting factors to be computed. For the consistent
solution which simultaneously adjusts hierarchical microdata (e.g. household
and personal information), a fast numerical solution by a specific modified
Newton-Raphson (MN) procedure with a global exponential approximation is
proposed by Merz (1994). 
This procedure involes numerically solving of a set of non-linear equations.

I'm aware of
http://www.stata.com/support/faqs/lang/nl.html.
I was wondering if it were possible to solve a set of non-linear equations
with Mata (So far, I have't used Mata but I'd like to invest the time to
learn it if it helps me solving this problem)? If yes, any hints on how to
tackle this problem are highly appreciated.  
Does somebody know any other programs for Stata/Mata that allow reweighting
of microdata?

Many thanks and best wishes for a nice weekend!
Andreas

Ref.:
Merz, Joachim (1994): Microdata Adjustment by the Minimum Information Loss
Principle. Unpublished.
http://mpra.ub.uni-muenchen.de/7231/


--------------------------------------------------------
Dr. Andreas Peichl

Research Associate

IZA - Forschungsinstitut zur Zukunft der Arbeit GmbH 
IZA - Institute for the Study of Labor 
P.O. Box 7240, 53072 Bonn, Germany
Schaumburg-Lippe-Str. 5-9, 53113 Bonn, Germany
Phone: +49 (228) 3894-511; Fax: +49 (228) 3894-510
E-Mail: peichl@iza.org
Web: http://www.iza.org
Registered Office Bonn, District Court of Bonn, HRB 7745 
Represented by: Prof. Dr. Klaus F. Zimmermann (Director)
-------------------------------------------------------- 




*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index