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

Gary King's method and the "ecological fallacy"





On Tue 08 Jul 1997 13:48:37  Joyce Davis wrote:

> In today's NY Times there is an article, "Statistician Builds what may 
> be a Better Data Mousetrap", that discusses a new method of looking at 
> statistical data that seems to avoid "the ecological fallacy".  The 
> method, developed by Dr. Gary King at Harvard, ...
>

Karen Freeman's article in the 8 July Times is a reasonable lay 
description of King's method and its importance and offers some 
interesting commentary on the method by other scientists.  King has 
described the method in the book _A Solution to the Ecological Inference 
Problem: Reconstructing Individual Behavior from Aggregate Data_, 
published in April by Princeton University Press.  It is available in 
hardcover ($49.50 -- ISBN 0-691-01241-5) and paper ($16.50 -- ISBN 0-691-
01240-7).  I have written a brief review of the book which is scheduled to 
appear in Health Physics.

Although the Times headline describes King as a statistician, he is a 
political scientist and Professor of Government at Harvard (although he 
obviously knows a lot more statistics than the average bear).  
Development of his method was supported by the National Science 
Foundation and King has received the American Political Science 
Association's Gosnell Prize for the best methodological work in political 
science during 1995-96.  

His method is an application of constrained optimization and is closely 
related to Maximum Likelihood Estimation in statistics and to the 
algorithms underlying computer tomography and other "unfolding" problems.  
It has been extensively tested and provides confidence limits on the 
estimates in generates.

Software implementing King's method is available for downloading from his 
Web page  http://GKing.Harvard.edu .

Freeman's article mentions the potential application of King's method to 
Cohen's radon and lung cancer data.

Best regards.

Jim Dukelow
Pacific Northwest National Laboratory
Richland, WA

js_dukelow@pnl.gov

These thoughts are mine and have not been reviewed and/or approved by my 
management or by the U.S. Department of Energy.