Genosis, Wedho (2023) Pemodelan Indeks Kedalaman Kemiskinan di Indonesia Menggunakan Regresi Probit Biner dengan Efek Interaksi. Other thesis, Institut Teknologi Sepuluh Nopember.
Text
06211940000077-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2025. Download (3MB) | Request a copy |
Abstract
Indeks kedalaman kemiskinan merupakan suatu ukuran rata-rata kesenjangan pengeluaran masing-masing penduduk miskin terhadap garis kemiskinan, dimana semakin tinggi nilai indeks maka, semakin jauh rata-rata pengeluaran penduduk dari garis kemiskinan. Dari tahun 2019 indeks kedalaman kemiskinan di Indonesia meningkat seiring bertambahnya jumlah penduduk miskin. Indeks kedalaman kemiskinan yang mengalami kenaikan dikarenakan dampak dari pandemi COVID-19 sangat mempengaruhi kondisi ekonomi masyarakat Indonesia, sehingga hal tersebutlah yang menyebabkan jumlah penduduk miskin di Indonesia semakin meningkat. Untuk mencegah adanya kenaikan indeks kedalaman kemiskinan di Indonesia maka diperlukannya analisis lebih lanjut mengenai pendugaan variabel-variabel prediktor yang memengaruhi angka indeks kedalaman kemiskinan. Pada penelitian ini, metode yang digunakan adalah regresi probit biner dengan efek interaksi. Variabel respon indeks kedalaman kemiskinan yang digunakan dikategorikan menjadi dua yaitu indeks kedalaman kemiskinan rendah dan indeks kedalaman kemiskinan tinggi. Pengelompokan variabel prediktor didasarkan oleh angka indeks kedalaman kemiskinan dengan digunakan variabel prediktor sejumlah tujuh. Variabel prediktor yang signifikan setelah dilakukan pemodelan menggunakan regresi probit biner dengan efek interaksi adalah variabel Tingkat Pengangguran Terbuka, Tingkat Partisipasi Angkatan Kerja, Harapan Lama Sekolah dan variabel interaksi antara Tingkat Partisipasi Angkatan Kerja dan Harapan Lama Sekolah. Adapun ketepatan klasifikasi Indeks kedalaman kemiskinan yang diperoleh adalah sebesar 82,36%
====================================================================================================================================
Poverty gap index is a measure of the average expenditure gap of each poor population towards the poverty line, where the higher the index value, the farther the average population expenditure is from the poverty line. From 2019 the poverty gap index in Indonesia has increased along with the increase in the number of poor people. The poverty gap index which has increased due to the impact of the COVID-19 pandemic has greatly affected the economic conditions of the Indonesian people, so that this has caused the number of poor people in Indonesia to increase. In order to prevent an increase in the poverty gap index in Indonesia, further analysis is needed regarding the estimation of the predictor variables that affect the poverty gap index. In this study, the method used is binary probit regression with interaction effects. The response variable for the poverty gap index used is categorized into two, namely the low poverty gap index and the high poverty gap index. The grouping of predictor variables is based on the poverty gap index number using seven predictor variables. Significant predictor variables after modeling using binary probit regression with interaction effects are the variables Open Unemployment Rate, Labor Force Participation Rate, Years of School Expectation and the interaction variable between Labor Force Participation Rate and Years of School Expectations. The classification accuracy of the poverty gap index is 82.36%
Item Type: | Thesis (Other) |
---|---|
Uncontrolled Keywords: | Efek Interaksi, Indeks Kedalaman Kemiskinan, Regresi Probit Biner, Binary Probit Regression, Interaction Effect, Poverty Gap Index |
Subjects: | Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression |
Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
Depositing User: | Wedho Genosis |
Date Deposited: | 02 Mar 2023 07:12 |
Last Modified: | 02 Mar 2023 07:12 |
URI: | http://repository.its.ac.id/id/eprint/97729 |
Actions (login required)
View Item |