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

RE: st: RE: RE: RE: Re: Compositional data

From   "Nick Cox" <>
To   <>
Subject   RE: st: RE: RE: RE: Re: Compositional data
Date   Fri, 7 Mar 2008 19:01:22 -0000

Gary King is, as some here know better than I do, a very energetic, 
talented and productive political scientist at Harvard.

I believe he used Gauss at the time referred to. Latterly he seems 
enamoured of R. Let a thousand flowers bloom! However, many of his 
students and former students use Stata, and (last I looked) he was very
publicising my -triplot- as a way to do these plots. 


Clive Nicholas

Further afield, Gary King and his colleagues did use Stata (via their
-clarify- routine, since abandoned) to illuminate the value of
electoral triangles (or 'ternary plots' as they called them) by
building upon a previous study of the 1988 Mexican presidential
election. Using survey data, they ran 100 multinomial-logit
simulations (why not 1000?) to estimate the effect of perceived
strength of the PRI party on the probabilities of each of the three
main candidates winning that election. They don't go into much detail,
but the results they do show are quite absorbing (King et al, 2000:

King G, Tomz M, and Wittenberg J (2000) "Making the Most of
Statistical Analyses: Improving Interpretation and Presentation,''
American Journal of Political Science 44(2): 347-361.

*   For searches and help try:

© Copyright 1996–2019 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index