The Generation of Industry Groups from Input—Output Data: A Comparison of Four Methods

A L Loviscek
Additional contact information
A L Loviscek: Division of Business and Economics, Indiana University—Purdue University at Fort Wayne, IN 46805, USA

Environment and Planning A, 1984, vol. 16, issue 6, 779-791

Abstract: Regional and urban analysts have developed graph-theoretic and multivariate approaches for decomposing the structure of flow tables. These developments have led to an important question: which method(s) should one use? In this study the author examines the ability of each of four approaches to generate industry groups (clusters) from a regional, survey-based input—output table. Specifically, the author deals with industry groups as generated by two graph-theoretic methods and by two multivariate techniques. The degree of similarity among the groups so generated is analyzed using measures of association. The composition of the groups depends on cutoff points. Nonetheless, the results suggest that one of the graph-theoretic methods and one of the multivariate techniques produce similar clusters. Further consideration indicates that these methods reveal more of the strongest interindustry linkages than their alternatives.

Date: 1984
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.sagepub.com/doi/10.1068/a160779 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sae:envira:v:16:y:1984:i:6:p:779-791

DOI: 10.1068/a160779

Access Statistics for this article

More articles in Environment and Planning A
Bibliographic data for series maintained by SAGE Publications ().