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.

      Pendekatan Geographically Weighted Random Forest dalam Pemodelan Prevalensi Stunting di Kabupaten/Kota Pulau Jawa Tahun 2024

      Thumbnail
      View/Open
      Cover (1.026Mb)
      Fulltext (2.433Mb)
      Lampiran (277.0Kb)
      Date
      2026
      Jenis/Type
      Skripsi
      Subtype
      Undergraduate Theses
      Author
      RIZAM, MOCH
      Silvianti, Pika
      Firdawanti, Aulia Rizki
      Metadata
      Show full item record
      Abstract
      Prevalensi stunting di Pulau Jawa masih menjadi permasalahan kesehatan masyarakat yang serius dengan karakteristik spasial yang bervariasi antar wilayah. Penelitian ini bertujuan memodelkan prevalensi stunting pada 119 kabupaten/kota di Pulau Jawa tahun 2024 menggunakan metode Geographically Weighted Random Forest (GWRF). Data penelitian bersumber dari Kementerian Kesehatan Republik Indonesia dan Badan Pusat Statistik, dengan peubah penjelas yang terdiri atas ASI eksklusif, sanitasi layak, akses air minum aman, kemiskinan, tingkat kelulusan SMA, gizi buruk, dan berat badan kurang. Sebelum pemodelan, dilakukan uji dependensi spasial dan heterogenitas spasial yang keduanya menunjukkan adanya efek spasial yang signifikan. Penentuan hyperparameter optimal menggunakan repeated cross-validation menghasilkan nilai mtry = 6 dan ntree = 100. Model GWRF optimal diperoleh menggunakan kernel adaptif dengan bandwidth 46 dan menghasilkan performa terbaik dengan RMSE sebesar 2,893 dan R2 0,643, mengungguli model RF global. Hasil penelitian menunjukkan bahwa kontribusi peubah penjelas bervariasi secara spasial, di mana wilayah Jawa bagian barat lebih dipengaruhi oleh peubah sanitasi, air minum, dan gizi buruk, Jawa bagian tengah oleh kemiskinan dan Pendidikan, serta Jawa bagian timur oleh peubah berat badan kurang. Temuan ini menegaskan efektivitas GWRF dalam mengungkapkan hubungan spasial secara adaptif dibandingkan pendekatan global.
       
      The prevalence of stunting in Java remains a serious public health concern, characterized by spatial variation across regions. This study aims to model stunting prevalence across 119 districts/cities in Java in 2024 using the Geographically Weighted Random Forest (GWRF) method. The data were obtained from the Ministry of Health of the Republic of Indonesia and the Central Bureau of Statistics, with explanatory variables comprising exclusive breastfeeding, adequate sanitation, access to safe drinking water, poverty, senior high school graduation rate, malnutrition, and underweight. Before modeling, tests for spatial dependency and spatial heterogeneity were conducted, both of which indicated significant spatial effects. Optimal hyperparameter tuning using repeated cross-validation yielded mtry = 6 and ntree = 100. The optimal GWRF model was obtained using an adaptive kernel with a bandwidth of 46, achieving the best performance with RMSE values of 2,893 and R2 0,643, outperforming the global RF model. The results indicate that the contribution of explanatory variables varies spatially, whereby western Java is more influenced by sanitation, drinking water, and severe malnutrition variables, central Java by poverty and education, and eastern Java by the underweight variable. These findings confirm the effectiveness of GWRF in adaptively capturing spatial relationships compared to global approaches.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/174517
      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