Pemodelan Robust Geographically Weighted Regression dengan Least Absolute Deviation pada Kasus Tuberkulosis di Jawa Barat

Abstract. Tuberculosis (TBC) is an infectious disease caused by Mycobacterium tuberculosis, which primarily affects the lungs but can also spread to other organs. Indonesia ranks second in the world for the highest number of TBC cases after India, with West Java Province contributing the most cases. This is likely due to the province's large population and high population density. TBC data is often analyzed using classical linear regression however, this method assumes a homogeneous relationship between variables across regions. In reality, differences in geographical, social, and economic conditions between areas lead to spatial variation and potential outliers in the data. This study applies the Robust Geographically Weighted Regression (RGWR) method with the Least Absolute Deviation (LAD) approach to model TBC cases in West Java in 2023. The RGWR-LAD method effectively addresses outliers and spatial heterogeneity. The results show that R-square values and significant variables vary across regions. However, the variables percentage of poor population and population density tend to consistently influence TBC cases in most areas. Abstrak. Tuberkulosis (TBC) adalah penyakit infeksi menular akibat Mycobacterium tuberculosis yang umumnya menyerang paru-paru, tetapi bisa menyebar ke organ lain. Indonesia menempati peringkat kedua kasus TBC tertinggi di dunia setelah India, dengan Provinsi Jawa Barat sebagai penyumbang kasus terbanyak. Hal ini diduga karena tingginya populasi dan kepadatan penduduk di provinsi tersebut. Analisis TBC sering menggunakan regresi linier klasik, namun metode ini mengasumsikan hubungan antar variabel bersifat homogen di seluruh wilayah, padahal kondisi geografis, sosial, dan ekonomi tiap daerah berbeda. Perbedaan ini memunculkan variasi spasial serta potensi pencilan dalam data. Penelitian ini menerapkan metode Robust Geographically Weighted Regression (RGWR) dengan pendekatan Least Absolute Deviation (LAD) untuk memodelkan kasus TBC di Jawa Barat tahun 2023. Metode RGWR-LAD dapat menangani pencilan dan heterogenitas spasial. Hasil model menunjukkan bahwa nilai R-square dan variabel yang signifikan berbeda antar wilayah. Namun, variabel jumlah penduduk miskin dan kepadatan penduduk cenderung konsisten berpengaruh terhadap kasus TBC di sebagian besar wilayah.

Authors

Institutions

Publication Details

Journal
Bandung Conference Series Statistics
Published
2025-08-04
DOI
https://doi.org/10.29313/bcss.v5i2.20540
Primary Topic
Spatial and Panel Data Analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Pemodelan Robust Geographically Weighted Regression dengan Least Absolute Deviation pada Kasus Tuberkulosis di Jawa Barat

Nur Azizah Komara Rifai, Nur Hikmatun Nazilah
Bandung Conference Series Statistics
Spatial and Panel Data Analysis
article

Pemodelan Robust Geographically Weighted Regression dengan Least Absolute Deviation pada Kasus Tuberkulosis di Jawa Barat

Nur Azizah Komara Rifai, Nur Hikmatun Nazilah
article en

Abstract

Abstract. Tuberculosis (TBC) is an infectious disease caused by Mycobacterium tuberculosis, which primarily affects the lungs but can also spread to other organs. Indonesia ranks second in the world for the highest number of TBC cases after India, with West Java Province contributing the most cases. This is likely due to the province's large population and high population density. TBC data is often analyzed using classical linear regression however, this method assumes a homogeneous relationship between variables across regions. In reality, differences in geographical, social, and economic conditions between areas lead to spatial variation and potential outliers in the data. This study applies the Robust Geographically Weighted Regression (RGWR) method with the Least Absolute Deviation (LAD) approach to model TBC cases in West Java in 2023. The RGWR-LAD method effectively addresses outliers and spatial heterogeneity. The results show that R-square values and significant variables vary across regions. However, the variables percentage of poor population and population density tend to consistently influence TBC cases in most areas. Abstrak. Tuberkulosis (TBC) adalah penyakit infeksi menular akibat Mycobacterium tuberculosis yang umumnya menyerang paru-paru, tetapi bisa menyebar ke organ lain. Indonesia menempati peringkat kedua kasus TBC tertinggi di dunia setelah India, dengan Provinsi Jawa Barat sebagai penyumbang kasus terbanyak. Hal ini diduga karena tingginya populasi dan kepadatan penduduk di provinsi tersebut. Analisis TBC sering menggunakan regresi linier klasik, namun metode ini mengasumsikan hubungan antar variabel bersifat homogen di seluruh wilayah, padahal kondisi geografis, sosial, dan ekonomi tiap daerah berbeda. Perbedaan ini memunculkan variasi spasial serta potensi pencilan dalam data. Penelitian ini menerapkan metode Robust Geographically Weighted Regression (RGWR) dengan pendekatan Least Absolute Deviation (LAD) untuk memodelkan kasus TBC di Jawa Barat tahun 2023. Metode RGWR-LAD dapat menangani pencilan dan heterogenitas spasial. Hasil model menunjukkan bahwa nilai R-square dan variabel yang signifikan berbeda antar wilayah. Namun, variabel jumlah penduduk miskin dan kepadatan penduduk cenderung konsisten berpengaruh terhadap kasus TBC di sebagian besar wilayah.

Bandung Conference Series StatisticsVol. 5(2)
Bandung Islamic University (ID)
Openalex Percentile: Top 71%
Spatial and Panel Data Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.