IPB University Logo

SCIENTIFIC REPOSITORY

IPB University Scientific Repository collects, disseminates, and provides persistent and reliable access to the research and scholarship of faculty, staff, and students at IPB University

AI Repository
 
Building and Categories


      View Item 
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Statistics and Data Sciences
      • View Item
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Statistics and Data Sciences
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Penggerombolan Spasio-Temporal Determinan Stunting di Indonesia Menggunakan K-Medoids dengan Weighted Euclidean Distance

      Thumbnail
      View/Open
      Cover (478.1Kb)
      Fulltext (1.333Mb)
      Lampiran (246.0Kb)
      Date
      2026
      Jenis/Type
      Skripsi
      Subtype
      Undergraduate Theses
      Author
      SALMA, YUMNA
      Anisa, Rahma
      Alamudi, Aam
      Metadata
      Show full item record
      Abstract
      Stunting masih menjadi masalah kesehatan masyarakat utama di Indonesia meskipun prevalensinya menurun menjadi 19,8% pada tahun 2024. Perbedaan kondisi geografis dan tingkat pembangunan wilayah mengharuskan adanya pendekatan analisis yang mampu mengelompokkan provinsi di Indonesia berdasarkan karakteristik risiko stunting yang dilihat berdasarkan kemiripan kondisi geografis dan pola dinamika perubahan dari tahun ke tahun. Penelitian ini terdiri atas 34 amatan provinsi menggunakan tiga peubah penyebab stunting, yaitu akses sanitasi layak, cakupan imunisasi dasar, dan prevalensi ketidakcukupan pangan. Sehingga, penelitian ini bertujuan mengidentifikasi pola spasio-temporal faktor risiko stunting antar provinsi di Indonesia menggunakan penggerombolan kmedoids. Ukuran kemiripan dinamika temporal dilakukan menggunakan pendekatan complexityi invariant-distance (CID), sedangkan kedekatan spasial menggunakan pendekatan k-nearest neighbors (KNN) berbasis jarak harvesine. Kedua komponen tersebut kemudian diintegrasikan menggunakan weighted euclidean distance (WED). Hasil penggerombolan menghasilkan tiga gerombol dengan tingkat risiko stunting yang berbeda. Gerombol risiko rendah menunjukkan kondisi yang lebih baik, gerombol risiko sedang menunjukkan kondisi transisi dan memerlukan perbaikan pada beberapa faktor, sedangkan gerombol risiko tinggi masih memerlukan perbaikan pada akses sanitasi, ketahanan pangan, dan cakupan imunisasi dasar. Aspek temporal (0,69) lebih dominan dibandingkan aspek spasial (0,31), sehingga pendekatan k-medoids berbasis WED efektif dalam menggambarkan pola spasio-temporal faktor determinan stunting di Indonesia periode 2021–2024.
       
      Stunting remained a major public health problem in Indonesia despite its prevalence declining to 19.8% in 2024. Indonesia's geographical diversity and regional development disparities required a spatio-temporal clustering approach to group provinces with similar stunting determinants. This study involved 34 provincial observations and analyzed three determinants of stunting, access to improved sanitation, complete basic immunization coverage, and the prevalence of undernourishment. Therefore, this study aimed to identify the spatio-temporal patterns of stunting risk factors across Indonesian provinces using k-medoids clustering. Temporal similarity was measured using the complexity invariant distance (CID), while spatial proximity was measured using Haversine distancebased k-nearest neighbors (KNN). These two components were then integrated using the weighted euclidean distance (WED). Clustering results identified three different stunting risk clusters. Provinces in the low-risk cluster generally exhibited better conditions across the three determinants, whereas those in the moderate-risk cluster showed transitional characteristics. Provinces in the high-risk cluster still required substantial improvements in access to improved sanitation, food security, and complete basic immunization coverage. The temporal aspect (0.69) was more dominant than the spatial aspect (0.31), indicating that the WED-based K-Medoids approach effectively captured the spatio-temporal patterns of stunting determinants in Indonesia during the 2021–2024 period.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/175698
      Collections
      • UF - Statistics and Data Sciences [166]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository