PREDICTIVE MODELING USING MULTIPLE REGRESSION: A CASE STUDY ON SOCIOECONOMIC INDICATORS

Abstract

Predictive modeling plays a central role in socioeconomic research by enabling analysts to quantify how demographic and macroeconomic factors contribute to income variation. Multiple regression is among the most widely used techniques for this purpose, offering a structured framework to evaluate the combined influence of education, age, employment status, household characteristics, GDP per capita, and inflation on household income. Using a well-structured synthetic dataset, the analysis integrates descriptive statistics, correlation patterns, and regression diagnostics to demonstrate the methodological processes required for rigorous predictive modeling. The findings reveal weak empirical relationships between the selected variables and income an expected outcome given the artificial nature of the dataset yet they provide valuable insights into model construction, assumption testing, and the interpretation of statistical outputs. By emphasizing analytical transparency and methodological clarity, the study illustrates how regression-based predictive frameworks can be applied to socioeconomic indicators, reinforcing their importance for academic inquiry and policy-oriented analysis.