Beyond Linear Insights in the Feldstein–Horioka Puzzle: Delving Into Monotonic and Nonlinear Statistical Dependencies With Moving Windows
Insu Choi & Woo Chang Kim
Abstract
The Feldstein–Horioka puzzle hypothesizes that when there is complete capital mobility, domestic savings and investment should be weakly correlated. However, empirical data frequently challenge this. This study analyzes the dynamics between gross capital formation and gross savings across 102 countries. The results reveal that some nations (e.g., Albania, Bangladesh, India) have strong positive correlations indicating limited international capital mobility (supporting the hypothesis); whereas others (e.g., Argentina, Germany, Iceland) display weak or negative correlations, suggesting greater capital fluidity. Significance testing reveals that ~66% of the countries demonstrate positive correlations at 5% significance, whereas 34% show non‐significant relationships. Incorporating normalized mutual information captures nonlinear dependencies that traditional correlation measures may overlook. Continental analysis reveals substantial heterogeneity; North American countries exhibit the strongest average correlations (0.50) and Asian nations the lowest (0.35), with the highest variability. The findings underscore the need to explore country‐specific global economic intricacies and region‐specific policy formulation.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.