Although input-output tables are more or less confusing data collections, there are only few applications of multivariate data analysis for these data in the literature. In this paper we show an aggregation procedure and correspondence analysis, both based on X2-distances, in application to input-output tables. Especially correspondence analysis seems to be an ideal tool for these data. Tables for the Federal Republic of Germany from 1978 to 1986 are analyzed to expose structures (static analysis) and uncover structural changes (comparative-static analysis) for the 58 economic sectors included in that kind of data.
Keywords
- Correspondence Analysis
- Multivariate Data Analysis
- Aggregation Procedure
- Transition Formula
- Total Inertia
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.