Methods for Constructing Composite Indices: One for All or All for One?

In last years, the debate on the measurement of multidimensional phenomena has caused, within the worldwide scientific Community, a renewed interest thanks to the publication, in September 2009, of the Stiglitz report and, in March 2013, of the first report on “Equitable and Sustainable Well-being” (BES) by the Committee composed by Istat (Italian National Institute of Statistics) and CNEL (Italian Council for Economics and Labour). It is common awareness that a number of socioeconomic phenomena cannot be measured by a single descriptive indicator and that, instead, they should be represented with multiple dimensions. Phenomena such as development, progress, poverty, social inequality, well-being, quality of life, provision of infrastructures, etc., require, to be measured, the ‘combination’ of different dimensions, to be considered together as the proxy of the phenomenon. This combination can be obtained by applying methodologies known as composite indices (Salzman, 2003; Mazziotta and Pareto, 2011). This paper addresses the problem of summarizing a set of socio-economic indicators and aims to provide some general guidelines for the construction of a composite index. In particular, the attention is focused on the search of the most suitable method depending on the following factors: type of indicators (substitutable/non-substitutable), type of aggregation (simple/complex), type of comparisons to be made (relative/absolute), type of weights of the indicators (subjective /objective). As is known, in fact, building a composite index is a delicate task and full of pitfalls: from the obstacles regarding the availability of data and the choice of individual indicators, to their treatment in order to compare (normalization) and aggregate them (weighting and aggregation). Despite the problems mentioned, the composite indices are widely used by several international organizations for meas-