The aggregation of industry sectors in input-output modeling is a common step in a regional analysis process. The author develops an optimization-based approach for identifying aggregation schemes which minimize the resulting error or information loss. Example problems previously reported in the literature are utilized for demonstrating the effectiveness of this approach and point out the shortcomings of previously reported results.
Get full access to this article
View all access options for this article.
References
1.
BlinJCohenC, 1977, “Technological similarity and aggregation in input-output systems: A cluster-analytic approach”Review of Economics and Statistics4482–91
2.
CabrerBContrerasDMiraveteE, 1991, “Aggregation in input-output tables: How to select the best cluster linkages”Economic Systems Research399–109
3.
GibbonsJWolskyATolleyG, 1982, “Approximate aggregation and error in input — output models”Resources and Energy4203–230
4.
KymnK, 1990, “Aggregation in input-output models: A comprehensive review, 1946–71”Economic Systems Research265–93
5.
LINDO Systems, 1995LINGO User's Guide (LINDO Systems, Chicago, IL)
6.
MurrayA, 1997, “Aggregation error minimization in input-output modeling”, paper presented at Western Regional Science Association 36th Annual Meeting, Hawaii, 23–26 February; copy available from the author
7.
OksanenEWilliamsJ, 1992, “An alternative factor-analytic approach to aggregation of input — output tables”Economic Systems Research4245–256
8.
RoyJBattenDLesseP, 1982, “Minimizing information loss in simple aggregation”Environment and Planning A14973–980
9.
SnickarsFWeibullJ W, 1977, “A minimum information principle: Theory and practice”Regional Science and Urban Economics7136–168
