Clustering Validation in the Context of Hierarchical Cluster Analysis: An Empirical Study

Author:

Silva Osvaldo,Sousa Áurea,Bacelar-Nicolau Helena

Abstract

AbstractThe evaluation of clustering structures is a crucial step in cluster analysis. This study presents the main results of the hierarchical cluster analysis of variables concerning a real dataset in the context of Higher Education. The goal of this research is to find a typology of some relevant items taking into account both the homogeneity and the isolation of the clusters. Two similarity measures, namely the standard affinity coefficient and Spearman’s correlation coefficient, were used, and combined with three probabilistic (AVL, AVB and AV1) aggregation criteria, from a parametric family in the scope of the VL (Validity Link) methodology. The best partitions were selected based on some validation indices, namely the global STAT levels statistics and the measures P(I2, Σ) and γ, adapted to the case of similarity coefficients. In order to evaluate the clusters and identify their most representative elements, the Mann and Whitney U statistics and the silhouette plot were also used.

Publisher

Springer International Publishing

Reference19 articles.

1. Bacelar-Nicolau, H.: Analyse d’un Algorithme de Classification Automatique. Thèse de 3ème Cycle. ISUP, Paris VI (1972)

2. Bacelar-Nicolau, H.: Contributions to the Study of Comparison Coefficients in Cluster Analysis (in Portuguese). Univ. Lisbon (1980)

3. Bacelar-Nicolau, H.: On the distribution equivalence in cluster analysis. In: P. A., Devijver, & J. Kittler (eds.) Pattern Recognition Theory and Applications, NATO ASI Series, Series F. Computer and Systems Sciences, vol. 30, pp. 73–79. Springer - Verlag, New York (1987)

4. Bacelar-Nicolau, H., Nicolau, F. C., Sousa, Á., Bacelar-Nicolau, L.: Clustering of variables with a three-way approach for health sciences. Testing, Psychometrics, Methodology in Applied Psychology (TPM) (2014) doi: https://doi.org/10.4473/TPM21.4.56

5. Benzécri, J. P.: Analyse Factorielle des Proximités. Publication de l’Institut de Statistique de l’ Universite de Paris (ISUP), XIII et XIV (1965)

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3