Agglomerative hierarchical clustering analysis based on partially-ordered Hasse Graph of poverty indicators in East Java

Sabara, Ina Maya, Rozi, Fachrur ORCID: https://orcid.org/0000-0002-6380-0297 and Jauhari, Mohammad Nafie (2023) Agglomerative hierarchical clustering analysis based on partially-ordered Hasse Graph of poverty indicators in East Java. Presented at The 12th International Conference on Green Technology (ICGT 2022), 26-27 Oct 2022, Malang, Indonesia.

Preview

Text 14992.pdf - Published Version Available under License Creative Commons Attribution Non-commercial. Download (793kB) | Preview

Abstract

Poverty is a central issue in many countries, so one of the main goals of a country is to eradicate poverty. One of the efforts is to identify indicators that affect poverty using cluster analysis. In this research, we discuss cluster analysis using the agglomerative hierarchical clustering method based on the partially-ordered Hasse graph. Meanwhile, one form of facilitating cluster analysis is the Hasse graph. Therefore, this study was conducted to find out which areas have close or similar poverty indicators based on the partially-ordered Hasse graph and reduce the incidence of poverty in East Java. Before conducting cluster analysis, a multicollinearity test was carried out between poverty indicators, then the proximity between objects was determined using the Euclidean distance. Afterward, cluster analysis was performed using agglomerative methods (single linkage and complete linkage) to obtain the best cluster solution. The single linkage method provides the best solution consisting of five clusters. The results of the partially-ordered Hasse graph show that the fifth cluster becomes the top layer based on the Gini indicator. The fourth cluster becomes the top layer based on the depth index indicator. Last, the first cluster becomes the top layer based on the open unemployment rate indicator and life expectancy.

Item Type:	Conference (Paper)
Keywords:	agglomerative hierarchical clustering; Hasse Graph; Poverty; cluster validity test; partially-ordered
Subjects:	01 MATHEMATICAL SCIENCES > 0104 Statistics > 010401 Applied Statistics 01 MATHEMATICAL SCIENCES > 0104 Statistics > 010499 Statistics not elsewhere classified
Divisions:	Faculty of Mathematics and Sciences > Department of Mathematics Graduate Schools > Magister Programme > Graduate School of Mathematics Education
Depositing User:	Fachrur Rozi
Date Deposited:	14 Jun 2023 08:42

Downloads

Origin of downloads

Actions (login required)

View Item