Pemetaan Ketahanan Pangan di Indonesia Menggunakan Geographically Weighted Ordinal Logistic Regression

Reynilda, Citra Sindy (2024) Pemetaan Ketahanan Pangan di Indonesia Menggunakan Geographically Weighted Ordinal Logistic Regression. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2043211041_Undergraduate_Thesis.pdf Restricted to Repository staff only until 1 April 2027. Download (4MB) | Request a copy

Abstract

Kondisi ketahanan pangan di Indonesia masih berada di bawah rata-rata global bahkan Asia-Pasifik. Keadaan tersebut menandakan bahwa ketahanan pangan yang memadai bagi masyarakat masih menjadi tantangan yang cukup besar di Indonesia. Pada tahun 2023 terjadi penurunan Indeks Ketahanan Pangan (IKP) di beberapa provinsi yang menunjukkan adanya kemunduran kemampuan wilayah tersebut dalam menjaga stabilitas pangan. Terlihat pula tidak meratanya IKP antar provinsi dan adanya variasi yang mencerminkan perbedaan karakteristik kondisi yang memengaruhi ketahanan pangan di setiap wilayah. Hal tersebut menjadi dasar penelitian ini untuk mengidentifikasi faktor-faktor yang memengaruhi ketahanan pangan di Indonesia. Ketahanan pangan yang memiliki skala pengukuran berupa tingkatan (ordinal) dapat dianalisis menggunakan Regresi Logistik Ordinal. Namun, metode tersebut tidak mampu menggambarkan adanya pengaruh dari aspek spasial. Digunakan metode Geographically Weighted Ordinal Logistic Regression (GWOLR) sebagai pendekatan yang dapat menangkap variasi spasial dalam hubungan antara variabel prediktor dengan tingkatan IKP. Hasil pemodelan ketahanan pangan di Indonesia menggunakan GWOLR menunjukkan bahwa model terbaik terdiri atas lima variabel prediktor yang membentuk sembilan kelompok provinsi berdasarkan variabel yang berpengaruh signifikan, yakni laju pertumbuhan penduduk (X1), produktivitas tanaman padi (X2), persentase penduduk miskin (X4), prevalensi balita stunting (X5), dan umur harapan hidup (X6). Terbentuk sembilan kelompok berdasarkan kesamaan variabel prediktor yang berpengaruh signifikan terhadap ketahanan pangan setiap provinsi, dengan ketepatan klasifikasi sebesar 91,18%.
==================================================================================================================================
The condition of food security in Indonesia is still below the global average and even the Asia-Pacific. This situation indicates that adequate food security for the community is still a considerable challenge in Indonesia. In 2023, there will be a decline in the Food Security Index (FSI) in several provinces, which shows a decline in the region's ability to maintain food stability. It can also be seen that the FSI is uneven between provinces and there are variations that reflect the differences in the characteristics of conditions that affect food security in each region. This is the basis for this research to identify factors that affect food security in Indonesia. Food security that has a measurement scale in the form of levels (ordinal) can be analyzed using Ordinal Logistics Regression. However, the method is not able to describe the influence of spatial aspects. The Geographically Weighted Ordinal Logistic Regression (GWOLR) method is used as a more appropriate approach to capture spatial variations in the relationship between the predictor variable and the FSI level. The results of food security modeling in Indonesia using GWOLR show that the best model consists of five predictor variables that form nine provincial groups based on variables that have a significant effect, namely population growth rate (X1), rice crop productivity (X2), percentage of poor population (X4), prevalence of stunting toddlers (X5), and life expectancy (X6). Nine groups were formed based on the similarity of predictor variables that had a significant effect on food security in each province, with a classification accuracy of 91.18%.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Geographically Weighted Ordinal Logistic Regression, Spasial, Ketahanan Pangan. Food Security, Geographically Weighted Ordinal Logistic Regression, Spatial.
Subjects:	H Social Sciences > HA Statistics H Social Sciences > HA Statistics > HA30.6 Spatial analysis Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	Citra Sindy Reynilda
Date Deposited:	05 Feb 2025 06:41
Last Modified:	05 Feb 2025 06:41
URI:	http://repository.its.ac.id/id/eprint/118191

Actions (login required)

View Item