Estimasi Umur Menikah Menggunakan Regresi Linier Berdasarkan Faktor Demografis Di Desa Pringtulis

Abstrak

Marriage is one of the key demographic events influenced by various social and economic factors, as well as individual characteristics. Shifts in the age of first marriage in Indonesia reveal complex dynamics, ranging from early marriage to delayed marriage in modern society. This study aims to analyze the demographic factors influencing the age at marriage and to develop a predictive model using a linear regression approach. The method employed is a quantitative approach with a causal-explanatory design based on data mining applied to the population dataset of Pringtulis Village, comprising 359 data. The variables analyzed include gender, education, occupation, income, economic class, and residential area. The analysis process includes data preprocessing, classical assumption tests, multiple linear regression modeling using the backward elimination method, and model evaluation using statistical tests and error metrics. The results of the study indicate that education has a positive effect on age at marriage, while economic and regional factors tend to have a negative effect under certain conditions. The resulting model has a Root Mean Squared Error (RMSE) of 5.19, indicating that the average prediction error is within a range of ±5 years. Overall, the linear regression model is able to represent the relationship between variables fairly well, although there are still external factors, such as culture and the social environment, that have not been accounted for in the model.

Keywords: estimation, age at marriage, demographic factors, linear regression, data mining