Pemodelan Kejahatan di Indonesia dengan Metode Regresi Nonparametrik Spline Truncated

Cindy, Atma Aurelia Caroline (2023) Pemodelan Kejahatan di Indonesia dengan Metode Regresi Nonparametrik Spline Truncated. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003201190-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2025. Download (2MB) | Request a copy

Abstract

Proses pembangunan suatu negara akan berjalan lancar jika kejahatan dapat ditekan serendah-rendahnya, yang dimana hal tersebut juga dipengaruhi oleh peran aktif dan dukungan dari masyarakat. The Global Initiative Against Transnational Organized Crime (The Global Initiative) pada tahun 2021 mencatat indeks kriminal terhadap 193 negara yang bergabung sebagai anggota PBB, yang dimana Indonesia tercatat berada di tingkat ke-25 dengan skor 6,38. Sedangkan berdasarkan publikasi BPS tahun 2021, jumlah kejahatan di Indonesia dari tahun 2018-2020 mengalami penurunan. Untuk mencapai tujuan pembangunan berkelanjutan berdasarkan program SDGs, perlu diketahui jumlah kejahatan pada suatu wilayah, sebab dengan meningkatnya kejahatan berarti semakin rendah tingkat keamanan pada suatu wilayah. Dengan demikian perlu mengetahui faktor-faktor yang mempengaruhi jumlah kejahatan, sehingga dapat menekan persentase kejahatan melalui faktor-faktor yang mempengaruhinya. Penelitian ini akan memodelan kejahatan menggunakan regresi nonparametrik spline truncated sebab hubungan antara variabel respon yaitu kejahatan dengan kelima variabel prediktor yang diduga mempengaruhi tidak berpola serta terdapat perubahan pola hubungan pada sub interval terntentu. Berdasarkan penelitian, model regresi nonparametrik spline yang baik adalah dengan menggunakan kombinasi titik knot (1,2,1,3,1) dengan menghasilkan koefisien determinasi sebesar 88,28% dan diperoleh tiga variabel yang berpengaruh signifikan terhadap kejahatan di Indonesia tahun 2020 yaitu variabel laju pertumbuhan penduduk, IPM, dan rata-rata lama sekolah.
====================================================================================================================================================
The development process of a Nation will run smoothly if crime can be kept to a minimum, which is also influenced by the active role and support of the public community. The Global Initiative) in 2021 recorded a criminal index against 193 countries that joined as members of the United Nations, where Indonesia was recorded at the 25th level with a score of 6.38. Meanwhile, based on the publication of the Central Statistics Agency (BPS) for 2021, the number of crimes in Indonesia has decreased from 2018-2020. To achieve sustainable development goals based on the SDGs program, it is necessary to know the number of crimes in an area, because an increase in crime means a lower level of security in an area. Thus it is necessary to know the factors that influence the number of crimes, so that the percentage of crime can be reduced through the factors that influence it self. This study will model crime using spline truncated nonparametric regression because the relationship between the response variable, crime, with the five prediktor variables that are thought to influence is not patterned and there is a change in the relationship pattern at certain sub-intervals. Based on research, the best spline nonparametric regression model is to use a combination of knot points (1,2,1,3,1) to produce a determination coefficient of 88.28% and three variables are obtained that have a significant effect on crime in Indonesia in 2020, namely the rate variable population growth, HDI, and average length of schooling.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Crime, Indonesia, Knot, Non Parametric Regression Spline,Indonesia, Kejahatan , Knot, Regresi Non Parametrik Spline.
Subjects:	H Social Sciences > HA Statistics > HA31.3 Regression. Correlation
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Atma Aurelia Caroline Cindy
Date Deposited:	12 Feb 2023 00:33
Last Modified:	12 Feb 2023 00:33
URI:	http://repository.its.ac.id/id/eprint/96833

Actions (login required)

View Item