Pemodelan dan Pemetaan Persentase Penduduk Miskin Tiap Provinsi di Indonesia Menggunakan Geographically Weighted Panel Regression

Zafira, Aisya Attika (2025) Pemodelan dan Pemetaan Persentase Penduduk Miskin Tiap Provinsi di Indonesia Menggunakan Geographically Weighted Panel Regression. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2043211108-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (3MB) | Request a copy

Abstract

Persentase penduduk miskin di Indonesia dari tahun ke tahun mengalami penurunan, namun hal tersebut masih jauh dari target yang telah ditetapkan oleh pemerintah dalam RPJMN 2020 - 2024. Sebanyak 14 dari 34 provinsi di Indonesia masih dibawah target yang telah ditetapkan, sehingga hal tersebut masih menjadi tantangan karena terdapat keragaman karakteristik antar wilayah, dengan adanya keragaman antar wilayah tersebut, faktor yang signifikan mempengaruhi penurunan persentase penduduk miskin antar provinsi berbeda satu sama lain. Oleh karena itu, salah satu metode yang cocok digunakan adalah metode Geographically Weighted Panel Regression (GWPR). Data yang digunakan dalam penelitian ini adalah data persentase penduduk miskin, TPT, gini rasio, persentase rumah tangga yang memiliki rumah sendiri, TPAK, APS dan AHH berdasarkan tiap provinsi di Indonesia. Hasil penelitian GWPR persentase penduduk miskin diperoleh model yang sama untuk beberapa provinsi. Variabel yang berpengaruh signifikan terhadap persentase penduduk miskin diantaranya TPT, persentase rumah tangga yang memiliki rumah sendiri, TPAK, APS, dan AHH. Model GWPR merupakan model terbaik untuk menjelaskan persentase penduduk miskin dibandingkan model regresi data panel karena nilai AIC model GWPR sebesar -13,06 lebih kecil dari regresi data panel sebesar 73,72.
================================================================================================================================
The percentage of poor people in Indonesia has decreased from year to year, but this is still far from the target set by the government in the 2020 - 2024 RPJMN. As many as 14 of the 34 provinces in Indonesia are still below the target that has been set, so this is still a challenge. because there is a diversity of characteristics between regions, with this diversity between regions, the factors that significantly influence the reduction in the percentage of poor people between provinces are different from each other. Therefore, one method that is suitable to use is the Geographically Weighted Panel Regression (GWPR) method. The data used in this research are data on the percentage of poor people, TPT, Gini ratio, percentage of households that own their own house, TPAK, APS and AHH based on each province in Indonesia. The results of the GWPR research on the percentage of poor people obtained the same model for several provinces. Variables that have a significant effect on the percentage of poor people include TPT, percentage of households that own their own house, TPAK, APS, and AHH. The GWPR model is the best model to explain the percentage of poor people compared to the panel data regression model because the AIC value of the GWPR model is -13.06, which is smaller than the panel data regression of 73.72.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Geographically Weighted Panel Regression, Indonesia, Persentase Penduduk Miskin
Subjects:	H Social Sciences > HA Statistics > HA30.6 Spatial analysis
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	Aisya Attika Zafira
Date Deposited:	28 Jul 2025 02:44
Last Modified:	28 Jul 2025 02:44
URI:	http://repository.its.ac.id/id/eprint/121911

Actions (login required)

View Item