Please use this identifier to cite or link to this item:
http://repository.ipb.ac.id/handle/123456789/168494| Title: | Penerapan Spatial Panel Durbin Model dan Geographically Weighted Panel Regression pada Data Kemiskinan di Provinsi Jawa Barat |
| Other Titles: | Application of Spatial Panel Durbin Model and Geographically Weighted Panel Regression on Poverty Data in West Java Province |
| Authors: | Masjkur, Mohammad Susetyo, Budi Sulistiyowati, Anis |
| Issue Date: | 2025 |
| Publisher: | IPB University |
| Abstract: | Kemiskinan merupakan salah satu isu prioritas dalam Sustainable Development Goals (SDGs). Tahun 2024, Provinsi Jawa Barat menjadi provinsi dengan jumlah penduduk miskin terbanyak kedua di Indonesia. Penelitian ini bertujuan untuk mengidentifikasi peubah-peubah yang berpengaruh secara signifikan terhadap persentase penduduk miskin kabupaten/kota di Provinsi Jawa Barat tahun 2019–2023 menggunakan model spatial panel Durbin model (spatial panel SDM) dan geographically weighted panel regression (GWPR). Data yang digunakan merupakan data sekunder indikator kemiskinan Provinsi Jawa Barat tahun 2019–2023 yang bersumber dari Badan Pusat Statistik Provinsi Jawa Barat. Terdapat dependensi dan heterogenitas spasial pada data, sehingga model spatial panel SDM dan GWPR dapat digunakan. Model spatial panel SDM yang dibangun adalah model fixed effect spatial Durbin model (fixed effect SDM). Model tersebut menunjukkan bahwa rata-rata lama sekolah dan pengeluaran per kapita berpengaruh signifikan. Selain itu, lag spasial dari peubah persentase rumah tangga yang menempati rumah layak huni, persentase penduduk yang memiliki jaminan kesehatan daerah, dan rata-rata lama sekolah juga berpengaruh signifikan. Model GWPR dengan model regresi panel fixed effect dengan fixed kernel Gaussian sebagai fungsi pembobot terbaik membentuk model yang berbeda untuk setiap wilayah. Peubah rata-rata lama sekolah menjadi faktor dominan yang memengaruhi persentase penduduk miskin kabupaten/kota di Provinsi Jawa Barat. Poverty is one of the priority issues in the Sustainable Development Goals (SDGs). In 2024, West Java Province became the province with the second highest number of poor people in Indonesia. This study aims to identify the variables that significantly affect the percentage of poor people in districts/cities in West Java Province from 2019–2023 using the spatial panel Durbin model (spatial panel SDM) and geographically weighted panel regression (GWPR). The data used are secondary data on poverty indicators in West Java Province from 2019–2023, sourced from Statistics Indonesia of West Java. There is spatial dependence and heterogeneity in the data, so both the spatial panel SDM and GWPR models can be applied. The spatial panel SDM built in this study is a fixed effect spatial Durbin model (fixed effect SDM). The model shows that average years of schooling and expenditure per capita have significant effects. In addition, the spatial lags of the percentage of households living in proper housing, the percentage of population covered by local health insurance, and average years of schooling also have significant effects. The GWPR model, estimated using a fixed effect panel regression with a Gaussian fixed kernel as the optimal weighting function, produces distinct models for each region. Average years of schooling is the dominant factor influencing the percentage of poor people in districts/cities in West Java Province. |
| URI: | http://repository.ipb.ac.id/handle/123456789/168494 |
| Appears in Collections: | UT - Statistics and Data Sciences |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| cover_G1401211084_ce5a4e46eecd48aeb95879d23eaaa669.pdf | Cover | 654.26 kB | Adobe PDF | View/Open |
| fulltext_G1401211084_0714a11edf264bd7a692bc43e9440101.pdf Restricted Access | Fulltext | 1.34 MB | Adobe PDF | View/Open |
| lampiran_G1401211084_f663bf62ca3b4774a00e51536a92b033.pdf Restricted Access | Lampiran | 499.8 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.