Another Look on Choosing Factors: The International Evidence
33 Pages Posted: 18 Oct 2019
Date Written: October 9, 2019
Extending Fama and French’s (2018) study to international equity markets, we test nested and non-nested asset pricing models for North America, Europe, Asia (excluding Japan), and Japan. For testing non-nested models, we propose a new simulation methodology using a blocks bootstrap approach. Our approach, which accounts for factor dependencies, results in lower out-of-sample Sharpe ratios across all models and countries than Fama and French’s (2018) pairs bootstrap approach. While we confirm that the six-factor model that combines the market factor and size factor with the small stock spread factors for vlaue, profitability, investment and momentum, produces the highest maximum squared Sharpe ratio in most economies, we do not find such evidence for Asia (excluding Japan). Spanning regressions reveal that size does not matter in any of the international equity markets, whereas value matters in Europe, Asia (excluding Japan), and even in Japan.
Keywords: risk factors, maximum squared Sharpe ratio, asset pricing models, spanning regressions
JEL Classification: G12, G14
Suggested Citation: Suggested Citation