Why Not to Aggregate Up: The Influence of Aggregation on the Ordering of Distributions

Posted: 19 Feb 2008

See all articles by Stephen Howes

Stephen Howes

Australian National University (ANU) - Development Policy Centre; Australian National University (ANU) - Crawford School of Public Policy

Date Written: October 1993

Abstract

Researchers in many fields of economics often compare distributions using some criterion or another of inequality, poverty or welfare. It is standard practice to base such comparative analysis on aggregated data. But will the results obtained be dependent on the degree of aggregation of the data? This paper argues, on the basis of a simulation study, that they will be since the probability of obtaining a ranking can increase rapidly with the degree of aggregation. Aggregation exaggerates the differences between similar distributions and overlooks crossings at the lower tail. A change in research strategy where possible and statistical inference used in its place.

Suggested Citation

Howes, Stephen, Why Not to Aggregate Up: The Influence of Aggregation on the Ordering of Distributions (October 1993). LSE STICERD Research Paper No. 02, Available at SSRN: https://ssrn.com/abstract=1094727

Stephen Howes (Contact Author)

Australian National University (ANU) - Development Policy Centre ( email )

7 Liversidge Street (Bld 70)
Lennox Crossing
Canberra, 0200
Australia

Australian National University (ANU) - Crawford School of Public Policy

ANU College of Asia and the Pacific
J.G. Crawford Building, #132, Lennox Crossing
Canberra, Australian Capital Territory 0200
Australia

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
212
PlumX Metrics