The econometrics of finance and growth

This chapter reviews different econometric methodologies to assess the relationship between financial development and growth. It illustrates the identification problem, which is at the center of the finance and growth literature, using the example of a simple ordinary least squares estimation. It discusses cross-sectional and panel instrumental variable approaches to overcome the identification problem. It presents the time series approach, which focuses on the forecast capacity of financial development for future growth rates, and differences-in-differences techniques that try to overcome the identification problem by assessing the differential effect of financial sector development across states with different policies or across industries with different needs for external finance. Finally, it discusses firm- and household-level approaches that allow analysts to dig deeper into the channels and mechanisms through which financial development enhances growth and welfare, but pose their own methodological challenges.