Estimating access to drinking water and sanitation: the need to account for uncertainty in trend analysis
Nationally representative household surveys are the main source of data for tracking drinking water, sanitation and hygiene (WASH) coverage. However, all survey point estimates have a certain degree of error that must be considered when interpreting survey results for policy and decision making. In...
| Autores: | , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2019 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/188322 |
| Acceso en línea: | https://hdl.handle.net/2117/188322 https://dx.doi.org/10.1016/j.scitotenv.2019.133830 |
| Access Level: | acceso abierto |
| Palabra clave: | Water-supply--Developing countries Sanitation--Developing countries Water Sanitation and hygiene (WASH) Sampling errors Household surveys Compositional data Joint Monitoring Programme (JMP) Sustainable development goals Sanejament -- Països en vies de desenvolupament Aigua -- Abastament -- Països en vies de desenvolupament Àrees temàtiques de la UPC::Desenvolupament humà i sostenible::Desenvolupament humà::Aigua i sanejament |
| Sumario: | Nationally representative household surveys are the main source of data for tracking drinking water, sanitation and hygiene (WASH) coverage. However, all survey point estimates have a certain degree of error that must be considered when interpreting survey results for policy and decision making. In this article, we develop an approach to characterize and quantify uncertainty around WASH estimates. We apply it to four countries – Bolivia, Gambia, Morocco and India – representing different regions, number of data points available and types of trajectories, in order to illustrate the importance of communicating uncertainty for temporal estimates, as well as taking into account both the compositional nature and non-linearity of JMP data. The approach is found to be versatile and particularly useful in the WASH sector, where the dissemination and analysis of standard errors lag behind. While it only considers the uncertainty arising from sampling, the proposed approach can help improve the interpretation of WASH data when evaluating trends in coverage and informing decision making. |
|---|