R x C Ecological Inference: Bounds, Correlations, Flexibility and Transparency of Assumptions

Journal of the Royal Statistical Society, Vol. 172, No. 1, pp. 67-81

15 Pages Posted: 17 Oct 2011

See all articles by D. James Greiner

D. James Greiner

Harvard University - Center on the Legal Profession

Kevin M. Quinn

University of Michigan at Ann Arbor - Department of Political Science

Date Written: January 16, 2009

Abstract

Despite its potential pitfalls, ecological inference is an unavoidable part of some quantitative settings, including US voting rights litigation. In such applications, the analyst will typically encounter two-way tables with more than two rows and columns. Although several ecological inference methods are currently available for 2 x 2 tables, there are fewer options for analysing general R x C tables, and virtually none that model counts as opposed to fractions. We propose a count R x C method that respects the bounds deterministically, that allows for complex relationships between internal cell quantities, that is easily extensible and that results from transparent assumptions. We study the method via simulation, and then apply it to an example that is drawn from the state of Texas relevant to recent redistricting litigation there.

Keywords: ecological inference, R x C, voting rights act, racial bloc voting

JEL Classification: K41

Suggested Citation

Greiner, Daniel James and Quinn, Kevin M., R x C Ecological Inference: Bounds, Correlations, Flexibility and Transparency of Assumptions (January 16, 2009). Journal of the Royal Statistical Society, Vol. 172, No. 1, pp. 67-81. Available at SSRN: https://ssrn.com/abstract=1945005

Daniel James Greiner (Contact Author)

Harvard University - Center on the Legal Profession ( email )

1585 Massachusetts Avenue
Wasserstein Hall, Suite 5018
Cambridge, MA 02138
United States
(617) 496-4643 (Phone)

Kevin M. Quinn

University of Michigan at Ann Arbor - Department of Political Science ( email )

Ann Arbor, MI 48109
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
32
Abstract Views
320
PlumX Metrics