Pemodelan Jumlah Siswa Putus Sekolah Jenjang SMA di Provinsi Sumatera Utara Menggunakan Regresi Poisson Inverse Gaussian (PIG)

Abidin, Nabila Salma Kurnia (2025) Pemodelan Jumlah Siswa Putus Sekolah Jenjang SMA di Provinsi Sumatera Utara Menggunakan Regresi Poisson Inverse Gaussian (PIG). Diploma thesis, Institut Teknologi Sepuluh Nopember.

Text 2043211062-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2027. Download (2MB) | Request a copy

Abstract

Permasalahan yang dihadapi sektor pendidikan di Indonesia adalah tingginya jumlah siswa putus sekolah pada jenjang tertentu dengan capaian tertinggi berada pada jenjang Sekolah Menengah Atas (SMA). Provinsi Sumatera Utara merupakan provinsi dengan jumlah siswa putus sekolah tertinggi dengan persentase sebesar 17,82% pada tahun 2023. Hal tersebut menjadi dasar penelitian ini yang bertujuan untuk mengetahui faktor-faktor yang berpengaruh signifikan terhadap jumlah siswa putus sekolah jenjang SMA di Provinsi Sumatera Utara. Jumlah siswa putus sekolah merupakan data count dan terdapat kasus overdispersi. Oleh karena itu, digunakan Regresi Poisson Inverse Gaussian (PIG) yang dikenal memiliki performa yang lebih baik dibandingkan model Binomial Negatif dalam menganalisis kasus overdispersi. Analisis yang dilakukan meliputi mendeskripsikan karakteristik data, pemeriksaan multikolinearitas, analisis Regresi Poisson, pengujian overdispersi, analisis Regresi PIG, dan pemilihan model terbaik berdasarkan nilai Akaike Information Criterion (AIC). Berdasarkan hasil analisis, dapat diketahui bahwa karakteristik jumlah siswa putus sekolah jenjang SMA di Provinsi Sumatera Utara pada tahun 2023 mengalami peningkatan sebesar 458 siswa putus sekolah dibandingkan dengan tahun sebelumnya dengan rata-rata jumlah siswa putus sekolah sebesar 53 siswa putus sekolah di setiap kabupaten/kota. Tidak terdapat multikolinearitas antar variabel predikor, sehingga data dapat dianalisis menggunakan Regresi Poisson. Akan tetapi terdapat kasus overdispersi, sehingga untuk menganalisis kasus tersebut digunakan pemodelan dengan Regresi PIG. Berdasarkan model Regresi PIG yang terbentuk didapatkan hasil bahwa variabel prediktor yang memengaruhi jumlah siswa putus sekolah jenjang SMA di Provinsi Sumatera Utara tahun 2023 yaitu kepadatan penduduk, Angka Partisipasi Murni (APM), dan jumlah tenaga kependidikan.
==================================================================================================================================
The problem faced by the education sector in Indonesia is the high number of students dropping out of school at a certain level with the highest achievement being at the Senior High School (SMA) level. North Sumatra Province is the province with the highest number of school dropouts with a percentage of 17.82% in 2023. This is the basis for this study which aims to find out the factors that have a significant influence on the number of high school dropouts in North Sumatra Province. The number of students who dropped out of school is a count data and there are cases of overdispersion. Therefore, the Gaussian Poisson Inverse Regression (PIG) is used which is known to have better performance than the Negative Binomial model in analyzing cases of overdispersion. The analysis carried out includes describing data characteristics, multicollinearity check, Poisson Regression analysis, overdispersion testing, PIG Regression analysis, and selecting the best model based on the Akaike Information Criterion (AIC) values. Based on the results of the analysis, it can be seen that the characteristics of the number of high school dropouts in North Sumatra Province in 2023 have increased by 458 dropouts compared to the previous year with an average number of dropouts of 53 students in each district/city. There is no multicollinearity between predicator variables, so the data can be analyzed using Poisson Regression. However, there are cases of overdispersion, so to analyze these cases, PIG regression modeling is used. Based on the PIG Regression model that was formed, the results were obtained that the predictor variables that affect the number of high school dropouts in North Sumatra Province in 2023 are population density, Pure Participation Rate (APM), and the number of education personnel.

Item Type:	Thesis (Diploma)
Uncontrolled Keywords:	Putus Sekolah, Sumatera Utara, School Dropout, Poisson Inverse Gaussian (PIG), North Sumatra
Subjects:	Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	Nabila Salma Kurnia Abidin
Date Deposited:	22 Jan 2025 02:49
Last Modified:	22 Jan 2025 02:49
URI:	http://repository.its.ac.id/id/eprint/116504

Actions (login required)

View Item