PREDICTING THE CHARACTERISTICS OF DRIVER’S LICENSE APPLICANTS AT SATPAS POLRESTA MANOKWARI USING HIERARCHICAL MULTIPLE REGRESSION

Abstract

This research aims to predict the characteristics of driver's license (SIM) applicants at the SATPAS (Driver’s License Issuance Unit) Polresta Manokwari using Hierarchical Multiple Regression analysis. The study explores six key variables: gender, age, occupation, city, type of driver's license, and type of application, as predictors of applicant characteristics. The analysis was conducted using SPSS version 29, with data collected from the population of driver's license applicants since 2023. Three models were tested, with Model 3 being identified as the best predictor, explaining 7% of the variance in applicant characteristics (R² = 0.070). This model incorporates the variables of age, occupation, city, and type of application, while gender and driver's license class were found to have no significant individual impact. The partial t-test results show that age, occupation, city, and type of application significantly influence applicant characteristics, with negative regression coefficients indicating that an increase in these variables leads to a decrease in the predicted characteristics of SIM applicants. The study highlights practical implications for SATPAS, suggesting that service processes could be improved by considering demographic factors such as age and occupation in order to optimize resource allocation and reduce service complexity. However, the study has several limitations. The use of secondary data limits the completeness and accuracy of the analysis, and the limited number of variables results in a narrow interpretation of the factors influencing SIM applicants. Additionally, the model explains only a small portion of the variance in applicant characteristics, suggesting that other unmeasured factors, such as education level or driving experience, may play a more significant role. Furthermore, the findings are not generalizable to other regions, as local conditions may impact license application patterns. Future research should address these limitations by collecting primary data, expanding the range of variables, employing more sophisticated analytical methods, and exploring other regions. This would provide a more comprehensive understanding of the factors affecting driver's license applicants and contribute to enhancing the quality of SIM issuance services in Indonesia. Keywords: Driver's License, Prediction, Hierarchical Multiple Regression, Applicant Characteristics