Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: how to calculate the Standardized Duncan Index by duncan or duncan2 command?


From   "Simo Hansen" <[email protected]>
To   <[email protected]>
Subject   RE: st: how to calculate the Standardized Duncan Index by duncan or duncan2 command?
Date   Thu, 26 Apr 2007 09:38:48 +0300

Thanks for your kind concern Nick.
Standardized Duncan Index is formulated by P. Das Gupta, Demography, Vol.24,
No2. (May, 1987), pp.291-295 as follows:

Standardized Duncan= 50*Sum_i (T_i/T+t_i/t)/2*abs(P_i/P-Q_i/Q)

Where T_i=Male_i+Female_i for the year 1950.
	t_i=Male_i+Female_i for the year 1940
	P_i=Male_i/(Male_i+Female_i)
	P=sum_i Male_i/(Male_i+Female_i)
	Q_i= Female_i/(Male_i+Female_i)
	Q=sum_i Female_i/(Male_i+Female_i)
What this standardized Duncan index does is to control any change in the
overall percent distributions of the population by occupation.
Do you think this modification can be incorporated in -duncan- and duncan2_
Thank you very much.
Simo







-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of n j cox
Sent: 25 Nisan 2007 Çarşamba 15:42
To: [email protected]
Subject: Re: st: how to calculate the Standardized Duncan Index by duncan or
duncan2 command?

There are no precise references or equations or definitions here to bite 
on.

-duncan- and -duncan2- are commands on SSC written by Ben Jann. Looking
at the code, I can't see any hidden options.

My understanding is that the Duncan index (which has many other names,
dissimilarity index perhaps being the most common) is already
standardised, at least in the sense that it is free of units and scaled
to lie between 0 and 1. If you want standardisation in some other sense,
I think you will need to say what that is.

As far as I can recall, the Duncan index was invented by Gini.

Nick

Simo Hansen

In the segregarion literature, some researchers suggest to use "standardized
Duncan index". Can I use the duncan or duncan2 command with some options to
obtain the standardized Duncan index? Or Should I calculate this
standardized one by writing a small program?
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



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