Re: st: Composite Indicator of Multidimensional Poverty

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Mon, 19/4/10, amatoallah ouchen wrote:
> Asselin, L-M., (2002)
> ''Multidimensional poverty: Composite indicator
> of multidimensional poverty.'' Institut de Mathématique
> Gauss: Lévis, Québec.

A first look at this paper suggests to me that the author
mixes up so called "causal indicators" and "effect indicators"
(see: Bollen 1984, and Bollen and Lennox 1991). If I 
remember correctly multiple correspondence analysis is all 
about association between the observed indicators, which 
means that it is a model for effect indicators. However, 
some of the indicators used in the analysis are clear
examples of causal indicators, e.g. the variable
"Does a road pass by the community?" seems to me indicating
a cause of the latent poverty variable rather than being
caused by the latent poverty variable. The problem is that
using the information contained in a causal indicator 
requires a completely different strategy than using the 
information contained in a effect indicator. 

Hope this helps,
Maarten

Bollen, K. A. 1984. Multiple indicators: Internal 
consistency or no necessary relationship? Quality & 
Quantity 18(4): 399-385.

Bollen, K. A., and R. Lennox. 1991. Conventional wisdom on 
measurement: A structural equation perspective. 
Psychological Bulletin 110(2): 305-314.

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


      

*
*   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/