Publication Search

Improving the quality of Human Resources (HR) is a major challenge in facing global competition. Education as the main means of improving the quality of HR in Indonesia is still faced with the problem of inequality of access and quality between regions. This inequality causes disparities in educational development between urban and remote areas. This study focuses on grouping provinces in Indonesia based on aspects of educational development in 2023, using cluster analysis. Secondary data from the Central Statistics Agency (BPS) is used as the basis for analysis, including variables of average length of schooling, Gross Participation Rate (APK), Pure Participation Rate (APM), number of senior high schools, and community literacy development index. This study uses hierarchical and non-hierarchical cluster analysis methods to group provinces in Indonesia. The results of the hierarchical cluster analysis using the average linkage method show the most optimal cluster with the formation of three clusters. The first cluster consists of 31 provinces, the second cluster consists of 2 provinces, and the third cluster consists of 1 province. Data characteristics show large variations in the number of senior high schools and relative homogeneity in the average length of schooling between provinces.

Poverty in Aceh Province is a significant challenge with variation between districts/cities due to differences in access to education, health, job opportunities, and infrastructure. This study aims to group districts/cities in Aceh based on poverty indicators in 2021 in order to produce a more targeted policy basis. The research data consists of 23 poverty indicators obtained from secondary sources. Cluster analysis is applied using hierarchical (average linkage) and non-hierarchical (K-Means) methods to identify poverty patterns between regions. The results of the hierarchical cluster show that there are two main groups, namely the first cluster has low poverty rates, higher education, strong purchasing power, and low unemployment, while the second cluster has the opposite characteristics. The non-hierarchical analysis (K-Means) produced five clusters with significant differences in poverty levels, labor force participation, education, and economy. These findings provide a basis for the Aceh government to design poverty alleviation policies that focus on the specific needs of each cluster to accelerate the improvement of welfare in all districts/cities in Aceh Province.

Poverty means the inability to fulfill the basic needs of family members, both food and non-food.  In this study, we will analyze several indicators that are assumed to be factors that influence poverty in East Java in 2023, including East Java in 2023, including the percentage of poor people, life expectancy, average years of schooling, and unemployment rate. life expectancy, average years of schooling, and open unemployment rate using cluster analysis to group kabupatens. cluster analysis to group districts/cities into clusters based on the factors that influence poverty. factors that influence poverty. The data used is secondary data obtained through the Central Bureau of Statistics (BPS) website as much as 38 data. Then the data obtained were analyzed for data characteristics, multivariate normal distribution assumption test, independent assumption test, and cluster analysis. assumption test, multivariate normal distribution, independent assumption test, cluster analysis hierarchical, and non-hierarchical cluster analysis, and selection of the best method to determine the optimum cluster. optimum cluster. So that the results obtained data characteristics tend not to be equal, fulfill the multivariate normal distribution assumption test, dependent data. At Hierarchical clustering results obtained the grouping of districts/cities in East Java based on the factors that influence poverty into 5 based on factors that influence poverty into 5 clusters, with 7 districts/municipalities in cluster 1, 16 districts/municipalities in cluster 2, 10 districts/municipalities in cluster 3, 4 districts/municipalities in cluster 4. districts/municipalities in cluster 3, 4 districts/municipalities in cluster 4, and 1 district/municipality in cluster 5. Based on these results, differences in characteristics between clusters indicates that there are significant variations in poverty factors in each region. The results of the non-hierarchical clustering resulted in the grouping of districts/municipalities in East Java based on the factors affecting poverty into 2 clusters, with 13 clusters. factors that influence poverty as many as 2 clusters, with 13 cluster 1, 25 districts/cities in cluster 2. Also, the results of the ANOVA test results obtained the results of all variables of the factors that influencing poverty in districts/municipalities in East Java Province significantly on poverty.