Examining the dimensionality of Circular Economy metrics using Hierarchical Clustering on Principal Components

Abstract

The Circular Economy (CE) indices have become a valuable tool for supporting the development of policies that provide information that reduces environmental pressures and impacts. However, highly dimensional data identifying many CE indicators is impractical in application. This paper aims to create a composite index of the CE indicators using the Hierarchical Clustering on Principal Components (HCPC) to extract the meaning of the CE indicators, as reducing dimensionality can improve understanding of indicators and metrics. The advantage of the HCPC methodology over principal components analysis (PCA) alone involves applying objective clustering techniques to the PCA results, which results in a better cluster solution. This study analysed a dataset of 61 indicators obtained from De Pascale, Arbolino, Szopik-Depczyńska, Limosani, and Ioppolo (2021). The composite indices revealed the dimensions of industrial symbiosis (IS), CE strategies, and spatial applications of the CE and IS concepts. The bottom-up and top-down approaches for CE and IS strategies have been the main implementation approaches in different governments and regions.

Keywords

• Circular Economy
• Circular Economy indicators
• industrial symbiosis
• Hierarchical Clustering on Principal Components