We will use the Data Library to perform a cluster analysis and understand the spatiotemporal distribution of malaria incidence per sub-district. Monthly malaria incidences, computed as arithmetic average of values in that month during the 8-year period for each of the 58 subzobas , are used for the analysis. The processing sequence in the Data Library is provided in the PowerPoint presentation below.

For optimal viewing:
Click on the YouTube logo on the bottom left of the control menu. Adjust the resolution to 1080p. View in full screen mode.

Cluster Analysis

The iterative non-hierarchical clustering method groups the subzobas into a specific user-defined number of clusters. The Data Library generates the cluster centers and allocates the subzobas to the clusters based on proximity to initial centers, or “seeds”.

Exercise

• Following the example provided in the Cluster Analysis presentation above, cluster the data in 2, 3, 4, 5, 6 and above clusters.

• Identify which number of clusters provides the best spatio-temporal information on malaria incidence distribution.