The Statistical and Computational Revolution in Economic Growth Models: A Review of Theoretical Developments and Empirical Applications

Abstract

This paper examines the transformative role of statistics and computer science in advancing economic growth theory, with particular emphasis on the evolution from neoclassical models to endogenous growth frameworks. The study analyzes how enhanced computational capabilities, and statistical methodologies have enabled economists to develop more sophisticated models that better explain empirical observations of economic growth patterns. We review key theoretical developments, including Romer's innovation-driven growth model (1986, 1990), Lucas's human capital framework (1988), and subsequent contributions by Aghion-Howitt (1992) and Barro (1992). The analysis demonstrates how statistical tools, and computational advances have facilitated the integration of multiple growth determinants, including human capital accumulation, technological innovation, and public infrastructure investment. Our findings suggest that the synthesis of statistical methods and computational power has not only enhanced theoretical modeling but also improved empirical validation and policy formulation in growth economics. This review contributes to the understanding of how quantitative methodological advances have shaped modern growth theory and its practical applications.