On the Composite Indicators for Food Security: Decisions Matter!

During the past decades, there has been much debate on food security. A variety of indicators have been proposed in order to establish which countries are in need of improved food security status. The heterogeneity of existing indicators and the lack of consensus on how to compare and rank countries have motivated international organizations to build composite indexes to synthesize the information. The process of building composite indexes involves multiple choices that influence the outcome. This analysis aims at understanding how relevant and discretional may be the analyst's choice of algorithms to compute composite indexes for food security. To this extent, we have computed several composite indexes for food security by using data provided by the Food and Agriculture Organization, which includes a large set of proxies for food security, as emerged from the Committee on World Food Security Round Table. We compare different methods to impute, homogenize, weight, and aggregate data, in order to compute composite indexes and show how relevant are the choices to be made. We show that normalization and weighting are not very crucial decisions, whereas special attention has to be paid in choosing the data imputation and aggregation methods. By commenting on the implications that different measurement choices may have in terms of global index, we show that the index construction decisions matter.