A compositional approach for modelling SDG7 indicators: Case study applied to electricity access.

Abstract Monitoring energy indicators has acquired a renewed interest with the 2030 Agenda for Sustainable Development, and specifically with goal 7 (SDG7), which seeks to guarantee universal access to energy. The predominant criteria to monitor SDG7 are given in a set of individual indicators. Along this line, the UN indicators proposed in the 47th session of the UN Statistical commission are a practical starting point. A relevant characteristic of these indicators is that they can be expressed as proportions from a whole, i.e., they are compositions. Notably, directly implementing traditional multivariate models onto indicators that are proportions without an intermediate process can lead to spurious analysis. Here, we aim to assess the application of compositional data analysis(CoDa) to follow up on the temporal trend indicators of the energy sector in the context of SDG7, with a case study for the most affected areas addressing the problem of electricity access. Following CoDa methodology, we first use a log-ratio transformation to bring compositions to real space and then apply three multivariate methods: linear regression, generalized additive models and support vector machine. We also address other characteristic problems of the electricity access indicators, such as data quality, which was treated by considering models with interactions. In sum, CoDa facilitates a controlled management of the parts that make up population based indicators, suggesting that modelling evolution of compositions as individual components – even the standard splitting of country data into rural and urban "access to" indicator – should be avoided. Highlights • Three multivariate methods are applied to a compositional data description of electricity access indicators to model temporal trends. • Poor data quality of electricity access indicators is treated by considering models with interactions. • The approach facilitates a controlled management of the parts that make up population based indicators. [ABSTRACT FROM AUTHOR]