Abstract
Increases in the availability of reliable health data are widely recognised as essential for efforts to strengthen health-care systems in resource-poor settings worldwide. Effective health-system planning requires comprehensive and up-to-date information on a range of health metrics and this requirement is generally addressed by a Health Management Information System (HMIS) that coordinates the routine collection of data at individual health facilities and their compilation into national databases. In many resource-poor settings, these systems are inadequate and national databases often contain only a small proportion of the expected records. In this paper, we take an important health metric in Kenya (the proportion of outpatient treatments for malaria (MP)) from the national HMIS database and predict the values of MP at facilities where monthly records are missing. The available MP data were densely distributed across a spatiotemporal domain and displayed second-order heterogeneity. We used three different kriging methodologies to make cross-validation predictions of MP in order to test the effect on prediction accuracy of (a) the extension of a spatial-only to a space–time prediction approach, and (b) the replacement of a globally stationary with a locally varying random function model. Space–time kriging was found to produce predictions with 98.4% less mean bias and 14.8% smaller mean imprecision than conventional spatial-only kriging. A modification of space–time kriging that allowed space–time variograms to be recalculated for every prediction location within a spatially local neighbourhood resulted in a larger decrease in mean imprecision over ordinary kriging (18.3%) although the mean bias was reduced less (87.5%).
Highlights
Both spatial-only and space–time geostatistical prediction techniques generally rely on the fitting of a random function (RF) model parameterised with a stationary mean and variogram
The objective of this paper is to carry out a series of different geostatistical prediction exercises that predict missing values of malaria proportion (MP) within the Kenyan Health Management Information System (HMIS) to examine the effect on prediction accuracy of (a) the extension of a spatial-only to a space–time prediction approach, and (b) the replacement of a stationary space–time RF model which requires a single global space–time variogram with a locally varying space–time RF model, which allows the space–time variogram to vary across the study domain
Sample variogram structure was consistent across the different monthly sample variograms, which supported the use of the same class of variogram model throughout
Summary
Gething et al / Computers & Geosciences 33 (2007) 1337–1350 and unsampled locations are distributed through time as well as space, the replacement of spatial-only with space–time geostatistical approaches can offer several benefits including more data to support parameter estimation and prediction and, if present, the exploitation of temporal as well as spatial autocorrelation in observed values This has led to the development and application of space–time geostatistical models in a range of fields including agricultural (Stein, 1998), atmospheric (De Iaco et al, 2002; Nunes and Soares, 2005) and soil science (Douaik et al, 2005; Snepvangers et al, 2003). Where a property of interest displays heterogeneous first- and second-order characteristics, alternative non-stationary models may be more appropriate and yield more accurate predictions (Haas, 1995)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
