Ladun, Zairi (2026) Pemodelan Faktor-Faktor yang Memengaruhi Jumlah Kecelakaan Lalu Lintas Kota Surabaya Tahun 2024 Menggunakan Regresi Poisson Inverse Gaussian. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 06211940000005-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
06211940000005-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (2MB) | Request a copy |
Abstract
Kecelakaan lalu lintas masih menjadi permasalahan serius di Kota Surabaya, ditandai dengan peningkatan jumlah insiden dari 1.264 kejadian pada tahun 2022 menjadi 1.495 kejadian pada tahun 2024. Penelitian ini bertujuan untuk menganalisis faktor-faktor yang memengaruhi variasi jumlah kecelakaan lalu lintas pada tingkat kecamatan di Kota Surabaya selama tahun 2024. Data yang digunakan mencakup 25 kecamatan dengan variabel respon berupa jumlah kecelakaan lalu lintas, serta rata-rata volume kendaraan harian sebagai variabel eksposur. Variabel prediktor meliputi karakteristik sosial-ekonomi dan infrastruktur jalan, yaitu kepadatan penduduk, proporsi penduduk usia produktif, rata-rata lama sekolah penduduk, rata-rata panjang jalan, rata-rata lebar jalan, dan proporsi jalan beraspal. Analisis awal menunjukkan adanya overdispersi yang kuat pada data jumlah kecelakaan, sehingga pendekatan Regresi Poisson Inverse Gaussian (PIGR) digunakan dengan estimasi parameter melalui algoritma Berndt–Hall–Hall–Hausman (BHHH) berbasis Maximum Likelihood Estimation (MLE). Hasil pemodelan menunjukkan bahwa kepadatan penduduk, proporsi penduduk usia produktif, rata-rata lama sekolah, rata-rata panjang jalan, dan rata-rata lebar jalan berpengaruh positif dan signifikan terhadap jumlah kecelakaan lalu lintas. Sebaliknya, proporsi jalan beraspal berpengaruh negatif, yang mengindikasikan peran kualitas permukaan jalan dalam meningkatkan keselamatan lalu lintas. Signifikansi parameter dispersi (τ = 4,236) menegaskan ketepatan penggunaan model PIGR dalam menangkap heterogenitas dan variasi risiko kecelakaan antar kecamatan. Dari penelitian ini disimpulkan bahwa pola kecelakaan lalu lintas di Kota Surabaya merupakan hasil interaksi kompleks antara tekanan demografis, intensitas mobilitas perkotaan, dan karakteristik fisik jaringan jalan, sehingga upaya pengendalian kecelakaan perlu diarahkan secara terintegrasi pada aspek sosial dan infrastruktur.
========================================================================================================================================
Traffic accidents remain a serious challenge in the City of Surabaya, as reflected by an increase in reported cases from 1,264 incidents in 2022 to 1,495 incidents in 2024. This study aims to examine the factors influencing the variation in traffic accident counts across sub-districts in Surabaya during 2024. The analysis is conducted at the sub-district level, covering 25 administrative areas, with the number of traffic accidents as the response variable and average daily traffic volume included as an exposure variable. The explanatory variables represent social-economic and road infrastructure characteristics, including population density, the proportion of the productive-age population (15–64 years), average years of schooling, average road length, average road width, and the proportion of paved roads. Preliminary analysis indicates strong overdispersion in the accident count data, motivating the use of Poisson Inverse Gaussian Regression (PIGR). Model parameters are estimated using the Berndt–Hall–Hall–Hausman (BHHH) algorithm under the Maximum Likelihood Estimation framework. The results show that population density, the proportion of the productive-age population, average years of schooling, average road length, and average road width have positive and statistically significant effects on the number of traffic accidents. In contrast, the proportion of paved roads exhibits a negative effect, highlighting the role of road surface quality in improving traffic safety. The dispersion parameter is statistically significant (τ = 4,236), confirming the presence of overdispersion and validating the appropriateness of the PIGR model. This study concludes that traffic accident patterns in Surabaya are the result of complex interactions between demographic pressures, the intensity of urban mobility, and the physical characteristics of the road network. Therefore, accident control efforts need to be directed in an integrated manner at both social and infrastructure aspects.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Analisis Kecamatan, BHHH, District Analysis, Overdispersion, Poisson Inverse Gaussian Regression, Traffic Accident, Kecelakaan Lalu Lintas, Overdispersi, Regresi Poisson Inverse Gaussian |
| Subjects: | H Social Sciences > HA Statistics H Social Sciences > HA Statistics > HA31.3 Regression. Correlation. Logistic regression analysis. H Social Sciences > HE Transportation and Communications > HE5614.2 Traffic safety 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: | Ladun Zairi |
| Date Deposited: | 29 Jan 2026 03:44 |
| Last Modified: | 29 Jan 2026 03:44 |
| URI: | http://repository.its.ac.id/id/eprint/129695 |
Actions (login required)
 |
View Item |