Ecological inference, as traditionally defined, is the process of using aggregate (i.e., "ecological") data to infer discrete individual-level relationships of interest when individual-level data are not available. Existing methods of ecological inference generate very inaccurate conclusions about the empirical world- which thus gives rise to the ecological inference problem. Most scholars who analyze aggregate data routinely encounter some form of this problem.
EI (by Gary King) and EzI (by Kenneth Benoit and Gary King) are
freely available software that implement the statistical and graphical
methods detailed in Gary King's book A Solution to the Ecological
Inference Problem. These methods make it possible to infer the
attributes of individual behavior from aggregate data. EI works within
the statistics program Gauss and will run on any computer hardware and
operating system that runs Gauss (the Gauss module, CML, or
constrained maximum likelihood- by Ronald J. Schoenberg- is also
required). EzI is a menu-oriented stand-alone version of the program
that runs under MS-DOS (and soon Windows 95, OS/2, and HP-UNIX). EI
allows users to make ecological inferences as part of the powerful and
open Gauss statistical environment. In contrast, EzI requires no
additional software, and provides an attractive menu-based user
interface for non-Gauss users, although it lacks the flexibility
afforded by the Gauss version. Both programs presume that the user has
read or is familiar with A Solution to the Ecological Inference
Problem.
Also see related research.