Answers are grounded in this paper and cite their sources.
One way to extract valuable insights from large datasets is through cluster analysis. This statistical technique involves grouping data objects based on their similarities, aiming to create distinct groups where objects within each group share high similarities but differ significantly from objects in other groups. Cluster analysis, such as the OPTICS and ST-DBSCAN methods, can be utilized in various domains, including healthcare workforce and demographic data. In a case study focusing on health workers in East Lombok, these clustering methods were employed. The study aimed to present the outcomes of clustering health workers using OPTICS and ST-DBSCAN and determine the superior method through internal validation. The results from OPTICS revealed the formation of 5 clusters: cluster-1 with two sub-district members, cluster-2 with three members, cluster-3 with two members, cluster-4 with three members, and cluster-5 with seven members. Conversely, ST-DBSCAN produced only 2 clusters: cluster-1 with six members and cluster-2 with four members. Based on the internal validation findings, OPTICS emerged as the more effective method for categorizing health workers in East Lombok.
No takes yet. Share an insight, caveat, or question.
Hastuti et al. (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: