Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

RE: st: How to assign distribution of one variable to the other variable


From   <S.Jenkins@lse.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: How to assign distribution of one variable to the other variable
Date   Tue, 29 May 2012 09:49:23 +0100

-invcdf- can be applied to ordered categorical variables. My subsidiary
comment was whether the coarseness of the grouping might mean that you
didn't have much genuine information to work with in the substantive
sense. But that's your call and, on this, you'll presumably be guided by
what other researchers in your discipline think is appropriate. 
To take a specific example to illustrate my question: look at the
"Juhn-Murphy-Pierce" (JMP) decomposition which uses this sort of
transformation -- but was developed for variables such as earnings
amounts. (References in the help file to -jmp- by Ben Jann, on SSC.) If
you're trying to do a similar exercise, but with ordered categorical
variables, you may be able to do it (in the sense of implementing it),
but does the interpretation still work well? I don't know; I'm simply
asking.

For more on "relative distribution methods", see also Ben Jann's
presentation at
http://www.stata.com/meeting/germany08/jann_reldist_berlin08.pdf, and
references therein. The -reldist- command that Ben refers to is not
found with a -findit- search, and you might need to contact him directly
if it is of interest. (NB The literature refers to continuous variables,
not ordered categorical.)

Stephen

------------------------------

Date: Mon, 28 May 2012 14:39:11 +0000
From: meenakshi beri <berimeenakshi@hotmail.com>
Subject: RE: st: How to assign distribution of one variable to the other
variable

Thanks Stephen!
Yes, my health status variable is ordered categorical. Is there any
package or command parallel to -invcdf- which can be applied to ordered
categorical variables?

Regards,
Meenakshi

Meenakshi Beri
Graduate Teaching Assistant
Department of Economics
Wayne State University
dy5651@wayne.edu


> Subject: st: How to assign distribution of one variable to the other
variable
> Date: Mon, 28 May 2012 09:47:58 +0100
> From: S.Jenkins@lse.ac.uk
> To: statalist@hsphsun2.harvard.edu
>
> Is -invcdf- on SSC (by Ben Jann) what you are after? -findit invcdf-
>
> If so, I note that such transformations are usually applied to
> continuous (wage or income) variables rather than categorical ones --
I
> am guessing that your "health status" variable is ordered categorical.
> (So you observe health in some coarse groupings, rather than some
> underlying continuum.)
>
>
> Stephen


Stephen
------------------
Professor Stephen P. Jenkins <s.jenkins@lse.ac.uk>
Department of Social Policy and STICERD
London School of Economics and Political Science
Houghton Street, London WC2A 2AE, UK
Tel: +44(0)20 7955 6527
Changing Fortunes: Income Mobility and Poverty Dynamics in Britain, OUP
2011, http://ukcatalogue.oup.com/product/9780199226436.do
Survival Analysis Using Stata:
http://www.iser.essex.ac.uk/survival-analysis
Downloadable papers and software: http://ideas.repec.org/e/pje7.html


Please access the attached hyperlink for an important electronic communications disclaimer: http://lse.ac.uk/emailDisclaimer

*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index