Using Geographic Information Systems and Spatial Analysis Methods to Assess Household Water Access and Sanitation Coverage in the SHINE Trial

Abstract

Access to water and sanitation are important determinants of behavioral responses to hygiene and sanitation interventions. We estimated cluster-specific water access and sanitation coverage to inform a constrained randomization technique in the SHINE trial. Technicians and engineers inspected all public access water sources to ascertain seasonality, function, and geospatial coordinates. Households and water sources were mapped using open-source geospatial software. The distance from each household to the nearest perennial, functional, protected water source was calculated, and for each cluster, the median distance and the proportion of households within <500 m and >1500 m of such a water source. Cluster-specific sanitation coverage was ascertained using a random sample of 13 households per cluster. These parameters were included as covariates in randomization to optimize balance in water and sanitation access across treatment arms at the start of the trial. The observed high variability between clusters in both parameters suggests that constraining on these factors was needed to reduce risk of bias.

Keywords: geographic information systems; georeferenced dataset; spatial analysis; water access; water coverage.

Figure 1.

Households in the 2 districts were mapped by obtaining shape files for administrative boundaries (A), overlaying administrative boundaries on Google Earth imagery (B), and visually identifying and recording households using the ADD PATH tool in Google Earth (C). The jagged line in (C) is produced by the ADD PATH tool after sequentially selecting multiple households.

Figure 2.

Distribution of distance from household to closest water point across the Sanitation Hygiene Infant Nutrition Efficacy study area (A), and the median distance within clusters (B).

Figure 3.

Spatial water coverage by functional, protected, perennial, and unrestricted water points across the Sanitation Hygiene Infant Nutrition Efficacy study area. The insert shows households that fall into the 3 regions: within <500 m, <1500 m, and >1500 m of a water point.

Figure 4.

Seasonal variation of available functional water points showing water coverage during the wet and dry seasons. Abbreviations: CI, confidence interval; HH, household; IQR, interquartile range; SD, standard deviation.

Figure 5.

The proportion of the population covered by functional, protected, perennial, and unrestricted water points as distance from the water point changes.

Figure 6.

Modeling the cost of improving water coverage by mixing rehabilitation of broken boreholes and drilling for replacement boreholes based on fixed cost estimates for replacement and rehabilitation.