<abstract xmlns="http://www.w3.org/1999/xhtml"><p> The use of different objective functions in hierarchical aggregation procedures is examined in this paper. Specifically, we analyse the use of the original Intramax objective function, the sum-of-flows objective function, the sum-of-proportions-to-intra-regional-flows objective function, Smart’s weighted interaction index, the first and second CURDS weighted interaction indices, and Tolbert and Killian’s interaction index. The results of the functional regionalisation have been evaluated by self-containment statistics, and they show that the use of the original Intramax procedure tends to delineate operationally the most persuasive and balanced regions that, regarding the intra-regional flows, homogeneously cover the analysed territory. The other objective functions give statistically better but operationally less suitable results. Functional regions modelled using the original Intramax procedure were compared to the regions at NUTS 2 and NUTS 3 levels, as well as to administrative units in Slovenia. We conclude that there are some promising directions for further research on functional regionalisation using hierarchical aggregation procedures.</p></abstract>

The use of different objective functions in hierarchical aggregation procedures is examined in this paper. Specifically, we analyse the use of the original Intramax objective function, the sum-of-flows objective function, the sum-of-proportions-to-intra-regional-flows objective function, Smart’s weighted interaction index, the first and second CURDS weighted interaction indices, and Tolbert and Killian’s interaction index. The results of the functional regionalisation have been evaluated by self-containment statistics, and they show that the use of the original Intramax procedure tends to delineate operationally the most persuasive and balanced regions that, regarding the intra-regional flows, homogeneously cover the analysed territory. The other objective functions give statistically better but operationally less suitable results. Functional regions modelled using the original Intramax procedure were compared to the regions at NUTS 2 and NUTS 3 levels, as well as to administrative units in Slovenia. We conclude that there are some promising directions for further research on functional regionalisation using hierarchical aggregation procedures.

Intramax and other objective functions: The case of Slovenia

Department of Geodetic Engineering, Faculty of Civil and Geodetic Engineering, University of Ljubljana, Slovenia

Moravian Geographical Reports

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

{"article-title":"Intramax and other objective functions: The case of Slovenia"}

The use of different objective functions in hierarchical aggregation procedures is examined in this paper. Specifically, we analyse the use of the original...

Intramax and other objective functions: The case of Slovenia

Publié en ligne: 08 juil. 2016

Pages: 12 - 25

Reçu: 04 nov. 2016

Accepté: 04 juin 2016

DOI: https://doi.org/10.1515/mgr-2016-0007

Mots clés
Intramax, objective function, contiguity constraint, hierarchical aggregation, functional region, functional regionalisation, Slovenia

© 2016

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Intramax and other objective functions: The case of Slovenia

Publié en ligne: 08 juil. 2016

Pages: 12 - 25

Reçu: 04 nov. 2016

Accepté: 04 juin 2016

DOI: https://doi.org/10.1515/mgr-2016-0007

Mots clésIntramax, objective function, contiguity constraint, hierarchical aggregation, functional region, functional regionalisation, Slovenia

© 2016

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Mots clés
Intramax, objective function, contiguity constraint, hierarchical aggregation, functional region, functional regionalisation, Slovenia