Quality of life assessment: distributional inequality and statistical perspectives
by
Pranab Kumar Sen
University of North Carolina, Chapel Hill, USA

In measuring poverty, affluence and other socio-economic inequalities, there is a subtle quantification of the underlying response variable(s) that generally involve both quantitative and qualitative traits. This quantification enables us to make use of measures of central tendency and concentration or inequality, such as the Gini coefficient, in the formulation of suitable indexes. In a broader context of diversity and distributional inequality, there may be a relatively more qualitative flavour that could invalidate the use of such moment-like measures in formulating indexes. An extreme case is the multi-dimensional contingency tables with only a qualitative trait without a linear ordering; here the usual Lorenz ordering and stochastic ordering may not be tenable in the conventional sense. This scenario is examined more specifically in the context of Quality of Life (QOL) assessments where there is a distributional inequality pattern with predominantly qualitative traits. The usual measure of Quality-adjusted Life (QAL) and Quality of Life deficiency (QOLD) may lose their charms in the absence of a linear ordering of the categories. Alternative measures that are more appropriate in this context are formulated. Related statistical perspectives are appraised thoroughly.

Date received: November 2, 2000

Copyright © 2000 by the author(s). The author(s) of this document and the organizers of the conference have granted their consent to include this abstract in Atlas Conferences Inc. Document # cafr-89.