Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Jurnal Aplikasi Statistika & Komputasi Statistik Multica Science and Technology Prosiding Seminar Nasional Official Statistics
Andrea Tri Rian Dani
Unknown Affiliation
Humanities Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Energy Library & Information Science Mathematics Physics Social Sciences

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Multica Science and Technology

 1 
COMPARISON OF MEAN CENTERING REGRESSION AND SPLINE TRUNCATED NONPARAMETRIC REGRESSION ON FACTORS AFFECTING THE NUMBER OF CRIMES IN INDONESIA Felicia Joy Rotua Tamba; Liana Oklas Ranly; Andrea Tri Rian Dani; Meirinda Fauziyah; Narita Yuri Adrianingsih; Mislan Mislan
Multica Science and Technology (ACCREDITED-SINTA 5) Vol. 5 No. 1 (2025): Multica Science and Technology
Publisher : Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/fpp74f96

Abstract

Crime remains one of the major challenges facing Indonesia, with the national crime rate showing an upward trend in 2022. This increase is driven by various social, economic, and demographic factors. To investigate these influences, this study applies the nonparametric truncated spline regression method to identify the determinants of crime rates across provinces in Indonesia. The response variable is the number of recorded crimes, while the predictor variables include the percentage of people living in poverty, mean years of schooling, average monthly per capita expenditure on food and non-food items, number of beneficiary households, budget for food social assistance, liberty aspects from the Indonesia Democracy Index, and the percentage of people with mental disorders. The analysis reveals that the linear truncated spline regression model with three knot points provides the best fit, achieving a coefficient of determination (R²) of 87.31%. These findings highlight the model’s capability to capture complex, nonlinear relationships between socio-economic indicators, democratic freedoms, mental health, and crime incidence in Indonesia.
MAPPING CRIME-PRONE AREAS USING PRINCIPAL COMPONENT ANALYSIS (PCA) – CENTROID LINKAGE Yossy Candra; Andrea Tri Rian Dani
Multica Science and Technology (ACCREDITED-SINTA 5) Vol. 5 No. 1 (2025): Multica Science and Technology
Publisher : Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/57qngy96

Abstract

Cluster analysis is a method employed to categorize data or objects according to their degree of resemblance. Centroid linkage is an algorithm that can be utilized in the grouping process. Centroid Linkage employs a hierarchical methodology that categorizes things into tiers according to their degree of similarity. Nevertheless, multicollinearity issues frequently arise in cluster analysis scenarios. Optimization of the centroid linkage technique through principal component analysis (PCA) diminishes research variables and generates a new principal component to address the issue of multicollinearity. To assess the validity of the clusters, the Silhouette Coefficient (SC) was utilized. The case study included characteristics deemed pertinent to crime issues in 34 provinces in Indonesia in 2021. The analysis yielded six principal components (PCs) with eigenvalues of one or above. The results from the Centroid Linkage algorithm indicated that the optimal number of clusters is 2, with a silhouette coefficient (SC) value of 0.61, signifying a well-structured and effective clustering arrangement. The attributes and delineation of each established cluster can yield insights for identifying crime-prone regions.
Co-Authors Felicia Joy Rotua Tamba Liana Oklas Ranly Meirinda Fauziyah Mislan Muhammad Aldani Zen NARITA YURI ADRIANINGSIH Raditya Novidianto Syamsiar, Syamsiar Yossy Candra