The Partial Least Squares-Path Modeling for the building of Social Composite Indicators

Many social phenomena are complex and therefore dicult to measure and to evaluate. A phenomenon is dened as complex when the relevant aspects of a particular problem cannot be captured by using a single perspective. It is necessary to consider the concept formed by dierent dimensions, each representing dierent aspects of it, which interact with each other. For this reason, most of the time, the complexity implies also multidimensionality. The goal of much research in social, economic and political elds is to obtain a whole description of the various facets of this complex phenomenon, through a suitable synthesis of the associated elementary indicators. Research, in the last years, has been focusing on the development and use of a system of composite indicators in order to obtain a global description of a complex phenomenon and to convey a suitable synthesis of information. The existing literature oers several alternative methods for obtaining a composite indicators. In this context my research line is placed. In detail, my works focus on building of composite indicators system through to Structural Equation Modeling (SEM), specically with the use of Partial Least Squares-Path Modeling (PLS-PM), which allows you to estimate causal relationships, dened according to a theoretical model linking two or more latent complex concepts, each measured through a number of observable indicators. The aim of the work is to demonstrate how PLS-PM could help you to build composite indicators system, in order to provide a better measure of more complex social phenomena. To illustrate the importance of the PLS-PM, a social composite indicator will be described.