Abstract
This paper presents clusters of the world's countries obtained by a novel weighted clustering method. The approach is based on data representations with symbolic descriptions of age–sex structures. To obtain clusters with similar descriptions, a weighted clustering method is used which is suitable for data described with discrete distributions. In contrast to the classical approach, this method allows the population of each sex to be included in the clustering process, thereby obtaining a representative age–sex structure corresponding to all the countries contained in the cluster. Observing the data over time reveals clusters of countries with similar changes in their population age–sex distributions. The resulting population pyramids are presented for 1996, 2001, and 2006.
An online supplement to this paper is available at http://dx.doi.org/10.1080/00324728.2014.954597.
Supplemental data
Supplemental data for this paper can be accessed at http://dx.doi.org/10.1080/00324728.2014.954597.
Notes
1 Simona Korenjak-Černe is at the University of Ljubljana, Faculty of Economics, Kardeljeva ploščad 17, 1000 Ljubljana, Slovenia. E-mail: [email protected]. Nataša Kejžar is at the University of Ljubljana, Faculty of Medicine. Vladimir Batagelj is at the University of Ljubljana, Faculty of Mathematics and Physics.
2 The authors are grateful to the journal's anonymous reviewers for their constructive comments and suggestions, which have contributed significantly to the improvement of this paper. The work was supported in part by the Slovenian Research Agency, grant P1-0294.