Pemetaan Ketahanan Pangan di Indonesia Menggunakan Geographically Weighted Panel Regression

Abiba, Nisa (2025) Pemetaan Ketahanan Pangan di Indonesia Menggunakan Geographically Weighted Panel Regression. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2043221090-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (5MB) | Request a copy

Abstract

Ketahanan pangan merupakan aspek penting dalam menjamin keberlangsungan hidup masyarakat serta mendukung pembangunan nasional yang berkelanjutan. Salah satu indikator yang digunakan untuk menggambarkan ketahanan pangan dan merepresentasikan tingkat ketidakcukupan konsumsi pangan di Indonesia adalah Prevalence of Undernourishment (PoU). PoU di Indonesia menunjukkan adanya ketimpangan antarprovinsi serta mengalami perubahan dari waktu ke waktu yang menunjukkan dinamika temporal, sehingga diperlukan analisis yang mampu menangkap perbedaan antarwilayah sekaligus perubahan temporal. Oleh karena itu, penelitian ini menggunakan metode Geographically Weighted Panel Regression (GWPR), yaitu pendekatan yang menggabungkan Geographically Weighted Regression (GWR) dan regresi data panel. Hasil penelitian menunjukkan bahwa pemodelan GWPR menghasilkan model yang berbeda untuk setiap provinsi di Indonesia dengan kebaikan model sebesar 88,292%. Berdasarkan hasil pemetaan, faktor-faktor yang memengaruhi PoU periode 2018 hingga 2023 terbagi dalam 25 kelompok provinsi. Provinsi dalam satu kelompok umumnya berdekatan secara geografis dan memiliki kesamaan variabel prediktor yang berpengaruh signifikan terhadap PoU. Pada kelompok 24 dan 25, mayoritas variabel prediktor berpengaruh signifikan terhadap PoU, secara khusus indeks harga implisit PDRB, koefisien gini, Indeks Pembangunan Manusia (IPM), kepadatan penduduk, ketersediaan infrastruktur jalan per kapita, Indeks Kemahalan Konstruksi (IKK), dan Indeks Demokrasi Indonesia (IDI) berpengaruh signifikan terhadap PoU di Gorontalo dan Sulawesi tengah. Persentase nilai perdagangan domestik per PDRB, koefisien gini, IPM, kepadatan penduduk, ketersediaan infrastruktur jalan per kapita, IKK, dan IDI berpengaruh signifikan terhadap PoU di Maluku. PoU tahun 2022 berbeda signifikan dibandingkan 2023 karena tahun 2022 merupakan periode pasca pandemi sehingga kondisi pemulihan ekonomi, ketidakstabilan rantai pasok pangan serta keterbatasan distribusi pangan memengaruhi tingkat ketidakcukupan konsumsi pangan.
==================================================================================================================================
Food security is a crucial aspect in ensuring people’s survival and supporting sustainable national development. One indicator commonly used to describe food security and represent the level of insufficient food consumption in Indonesia is the Prevalence of Undernourishment (PoU). PoU in Indonesia shows disparities across provinces and changes over time, indicating both spatial differences and temporal dynamics. Therefore, an analytical approach that can capture regional variations as well as temporal changes is needed. This study employs the Geographically Weighted Panel Regression (GWPR) method, which combines Geographically Weighted Regression (GWR) and panel data regression. The results show that GWPR produces different models for each province in Indonesia, with an overall model goodness-of-fit of 88,292%. Based on the mapping results, factors influencing PoU during the 2018–2023 period are grouped into 25 provincial clusters. Provinces within the same cluster are generally geographically close and share similar significant predictor variables affecting PoU. In clusters 24 and 25, most predictor variables significantly influence PoU. Specifically, the implicit GRDP price index, Gini coefficient, Human Development Index (HDI), population density, road infrastructure availability per capita, Construction Cost Index (CCI), and Indonesian Democracy Index (IDI) significantly affect PoU in Gorontalo and Central Sulawesi. Meanwhile, the percentage of domestic trade value to GRDP, Gini coefficient, HDI, population density, road infrastructure availability per capita, CCI, and IDI significantly affect PoU in Maluku. Furthermore, PoU in 2022 differs significantly from 2023 because 2022 was a post-pandemic period. During this time, economic recovery conditions, food supply chain instability, and limitations in food distribution influenced the level of insufficient food consumption.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Geographically Weighted Panel Regression, Indonesia, Prevalence of Undernourishment (PoU), Geographically Weighted Panel Regression, Indonesia, Prevalence of Undernourishment (PoU)
Subjects:	H Social Sciences > HA Statistics > HA30.6 Spatial analysis
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	Nisa Abiba
Date Deposited:	02 Jan 2026 01:41
Last Modified:	02 Jan 2026 01:41
URI:	http://repository.its.ac.id/id/eprint/129182

Actions (login required)

View Item