Automatic biclustering of regions and sectors
(2016) , 32 pages
Files
ISBADP2016_42_mouchart_Automaticbiclusteringofregionsandsectors_dial.pdf
Open Access - Adobe PDF
- 2.99 MB
Details
- Authors
- Abstract
- This paper develops an automatic grouping procedure of regions and sectors based on a greedy biclustering algorithm, focused simultaneously on their relative regional specialization and relative industrial concentration. Based on an association measure for a contingency table (regions x sectors), this procedure enables to i) significantly reduce the size of the original table and obtain an optimal collapsed table with low level of information loss vis-à-vis the degree of global localization; and ii) identify the homogeneous regions according to the industrial structure in terms of sub- and over- specialization in large two-way contingency tables. The properties and results of the algorithm are discussed through the presentation of three applications, namely Argentina, Brazil and Chile. In particular, an object of discussion, in the case of Brazil, is the result that the number of cells of the original table is reduced by 99% while the lost global localization information is 23%.
- Affiliations
Citations
Haedo, C., & Mouchart, M. (2016). Automatic biclustering of regions and sectors (ISBA Discussion Paper 2016/42). https://hdl.handle.net/2078.5/180050