Statistical Clustering Approach: Mapping Population Indicators Through Probabilistic Analysis in Aceh Province, Indonesia

Abstract

The clustering, one of statistical analysis, can be used for understanding population patterns and as a basis for more targeted policy making. In this ecological study, we explored the population dynamics across 23 districts/cities in Aceh Province. The study used the Aceh Population Development Profile Year 2022 data, focusing on the total population, in-migrants, out-migrants, fertility, and maternal mortality as variables. The study employed descriptive statistics to ascertain the data distribution, followed by the Shapiro-Wilk test to evaluate normality, which is crucial for selecting the appropriate statistical methods. The Spearman test was used to determine correlations between the total population and the variable as indicators. Probabilistic Fuzzy C-Means (PFCM) method is used for clustering. To optimize clustering, the silhouette coefficient was calculated using the Euclidean Distance and the elbow method, with the results analyzed using R-4.3.2 software. This study's design and methods aim to provide a nuanced understanding of demographic patterns for targeted policy-making and regional development in Aceh, Indonesia. Based on the data normality test results, only fertility (p-value = 0.45), while the other variables are not normally distributed. Spearman test was used, and the results showed that only in-migrants (p-value = 1.78 x 10-6) and out-migrants (p-value = 2.30 x 10-6) correlated to the Aceh Province population. Using the population variable and the two variables associated with it, it was found that 4 is the best optimum number of clusters, where clusters 1, 2, 3, and 4 consist of three districts/city, nine districts/city, four districts/city and seven districts/city respectively.