Preprocessing alternatives for compositional data related to water, sanitation and hygiene

Sci Total Environ. 2020 Nov 15;743:140519. doi: 10.1016/j.scitotenv.2020.140519. Epub 2020 Jun 25.

Abstract

The Sustainable Development Goals (SDGs) 6.1 and 6.2 measure the progress of urban and rural populations in their access to different levels of water, sanitation and hygiene (WASH) services, based on multiple sources of information. Service levels add up to 100%; therefore, they are compositional data (CoDa). Despite evidence of zero value, missing data and outliers in the sources of information, the treatment of these irregularities with different statistical techniques has not yet been analyzed for CoDa in the WASH sector. Thus, the results may present biased estimates, and the decisions based on these results will not necessarily be appropriate. In this article, we therefore: i) evaluate methodological imputation alternatives that address the problem of having either zero values or missing values, or both simultaneously; and ii) propose the need to complement the point-to-point identification of the WHO/UNICEF Joint Monitoring Program (JMP) with other robust alternatives, to deal with outliers depending on the number of data points. These suggestions have been considered here using statistics for CoDa with isometric log-ratio (ilr) transformation. A selection of illustrative cases is presented to compare performance of different alternatives.

Keywords: Global monitoring; Mahalanobis distance; Outliers; Robust regression.