Pengelompokan Kabupaten/Kota di Jawa Barat Berdasarkan Akses Air Minum dan Sanitasi Layak Menggunakan Metode Ward
DOI:
https://doi.org/10.29313/bcss.v6i2.25291Keywords:
Ward’s Method, air minum layak, , sanitasi layakAbstract
Abstract. Access to adequate drinking water and sanitation remains uneven across regions in West Java Province. This study aims to cluster the 27 regencies/cities in West Java Province based on the percentage of households with access to adequate drinking water sources and adequate sanitation in 2024 using Agglomerative Clustering with Ward’s Method. The data used were obtained from Statistics Indonesia (BPS). The analysis stages included outlier detection using the Interquartile Range (IQR), multicollinearity testing using the Variance Inflation Factor (VIF), Euclidean distance calculation, and determination of the optimal number of clusters based on the Silhouette Index (SI) and Calinski–Harabasz Index (CHI). The results showed that there were no outliers or multicollinearity in the two variables. Evaluation of cluster numbers from 2 to 5 indicated that three clusters were the optimal configuration, with an SI value of 0.55 and a CHI value of 84.87. The clustering results using Ward’s Method formed Cluster 0, consisting of 13 regencies/cities with high and relatively even access to adequate drinking water and sanitation; Cluster 1, consisting of 7 regencies/cities with good access to adequate drinking water but moderate access to adequate sanitation; and Cluster 2, consisting of 7 regencies/cities with the lowest access to adequate drinking water and sanitation. These findings can serve as a basis for formulating more targeted policies for drinking water and sanitation infrastructure development in West Java Province.
Keywords: Ward’s Method, adequate drinking water, adequate sanitation.
Abstrak. Akses terhadap air minum dan sanitasi layak masih menunjukkan ketimpangan antarwilayah di Provinsi Jawa Barat. Penelitian ini bertujuan mengelompokkan 27 kabupaten/kota di Provinsi Jawa Barat berdasarkan persentase rumah tangga dengan akses sumber air minum layak dan sanitasi layak tahun 2024 menggunakan Agglomerative Clustering dengan Ward’s Method. Data yang digunakan bersumber dari Badan Pusat Statistik (BPS). Tahapan analisis meliputi pemeriksaan outlier menggunakan Interquartile Range (IQR), pengujian multikolinearitas menggunakan Variance Inflation Factor (VIF), perhitungan jarak Euclidean, serta penentuan jumlah klaster optimal berdasarkan Silhouette Index (SI) dan Calinski–Harabasz Index (CHI). Hasil pengujian menunjukkan tidak terdapat outlier maupun multikolinearitas pada kedua variabel. Evaluasi jumlah klaster 2 hingga 5 menunjukkan bahwa tiga klaster merupakan konfigurasi optimal dengan nilai SI sebesar 0,55 dan CHI sebesar 84,87. Hasil clustering dengan Ward’s Method membentuk Klaster 0 sebanyak 13 kabupaten/kota dengan akses air minum dan sanitasi layak yang tinggi dan merata, Klaster 1 sebanyak 7 kabupaten/kota dengan akses air minum baik namun sanitasi pada tingkat menengah, serta Klaster 2 sebanyak 7 kabupaten/kota dengan akses air minum dan sanitasi layak paling rendah. Hasil penelitian ini dapat menjadi dasar dalam perumusan kebijakan pembangunan infrastruktur air minum dan sanitasi yang lebih tepat sasaran di Provinsi Jawa Barat.
Kata Kunci: Ward’s Method, air minum layak, sanitasi layak..
References
Bimantoro Putra, F., Tri Rian Dani, A., & Wigantono, S. (2023). Penerapan Algoritma Hierarchical Clustering dalam Pengelompokkan Kabupaten/Kota di Papua Berdasarkan Indikator Kemiskinan.
Kesuma, R., & Purwoto, A. (2022). Pengelompokan Kabupaten/Kota Berdasarkan Indikator Rumah Layak Huni di Provinsi Jawa Barat Tahun 2020. Seminar Nasional Official Statistics.
Murtagh, F., & Legendre, P. (2011). Ward’s Hierarchical Clustering Method: Clustering Criterion and Agglomerative Algorithm. https://doi.org/10.1007/s00357-014-9161-z
Naluba, Zornata, R., Cynthia, O. U., Biu, & Oyinebifun, E. (2023). Modelling and Detecting Multicollinearity of Some Economic Variables on Gross Domestic Product using Variance Inflation Factor. International Journal of Mathematics Trends and Technology, 69(2), 61–69. https://doi.org/10.14445/22315373/ijmtt-v69i2p508
Rahmawati, F., & Imanuel Fallo, S. (2025). Hierarchical Agglomerative Clustering dengan Metode Ward untuk Pemetaan Pasar Tenaga Kerja Pascapandemi di Jawa Tengah: Pendekatan Machine Learning Berbasis Klasterisasi. Jurnal Matematika, 5.
Raja, N. A., Tinungki, G. M., & Sirajang, N. (2024). Implementasi Algoritma Centroid Linkage dan K-Medoids dalam Mengelompokkan Kabupaten/Kota di Sulawesi Selatan Berdasarkan Indikator Pendidikan. ESTIMASI: Journal of Statistics and Its Application, 5, 61–74. https://doi.org/10.20956/ejsa.v5i1.13605
Rena Mayasari, T. (2020). Clustering Akses Air Bersih dan Sanitasi Layak Kabupaten/Kota di Provinsi Lampung.
Rehman, A. ur, & Belhaouari, S. B. (2021). Unsupervised outlier detection in multidimensional Data. Journal of Big Data, 8(1). https://doi.org/10.1186/s40537-021-00469-z
Wang, X., & Xu, Y. (2019). An Improved Index for Clustering Validation Based on Silhouette Index and Calinski-Harabasz Index. IOP Conference Series: Materials Science and Engineering, 569(5). https://doi.org/10.1088/1757-899X/569/5/052024
