Spatial Clustered Regression Analysis of 2017 Getis Score Indonesian Malaria Prevalence Data

Abstract

Malaria is a disease that is still endemic to Indonesia. In the national scale, morbidity rate related to malaria continued to decline from 2009 to 2017. Eastern areas of Indonesia (namely Papua, West Papua, and East Nusa Tenggara) still have high endemic levels of malaria, while western areas (Islands Sumatera and Java) mostly have low endemic levels or even free of malaria. This indicates that malaria has a clustering pattern. This research used the Annual Parasite Incidence (API) data as the dependent variable and Slide Positivity Rate (SPR), Annual Blood Examination Rate (ABER), number of positive cases on children aged 1-14 years, and the number of Plasmodium falciparum cases and Plasmodium vivax cases data as the independent variables. Since they contain spatial autocorrelation, Getis Ord G_i were employed in the clustered regression analysis. Finite Mixture Model was employed as the clustering method. This study resulted in the forming of 3 clusters. Cities/regencies belonging to Cluster-1 were neither hotspots nor coldspots. Elements of Cluster-2 are SPR hotspots. Elements of Cluster-3 are hotspot areas of API, ABER, number of Plasmodium falciparum cases, number of Plasmodium vivax cases, and number of cases on children aged 1-14 years. Cluster-1 consists of 360 cities/regencies located in Islands Kalimantan, Sulawesi, Sumatera, and Java, and North Maluku Province. Cluster-2 consists of 88 cities/regencies, mostly located in provinces South Sumatera, Bengkulu, Lampung, Banten, DKI Jakarta, and West Java. Cluster-3 consists of 66 cities/regencies located in the Papua Island and East Nusa Tenggara Province.

Collaborative Governance and Environmental Regulation Measures for Pollution Reduction and Carbon Reduction in the Yangtze River Basin under the “Double Carbon” Goal

“…In order to improve the accuracy of research on the impact of environmental regulations on carbon emissions in the Yangtze River Basin, it is necessary to analyze the characteristics of time and space [32,33]. For traditional regression analysis, data with spatial properties cannot be analyzed [34,35]. In related studies, the researchers improved and optimized the econometric model.…”