The role of categorical EPU indices in predicting stock-market returns

This study investigates the predictive ability of categorical economic-policy uncertainty (EPU) indices for stock-market returns. The results indicate that some categorical EPU indices have superior predictive ability for stock returns and even achieve higher realized utility than the original EPU index and popular predictors. Furthermore, the diffusion indices based on EPU categories, especially those that use partial least squares (PLS) to extract the principal compo-nents, more effectively use the forecast information contained in categorical EPU indices, resulting in improved forecast performance, including reduced forecast errors and increased economic value for investors. In addition, the categorical EPU indices show superior forecasting performance during economic-expansion, the China-US trade-war, and COVID-19 pandemic periods.

Automated summary

This study examines the predictive ability of categorical economic-policy uncertainty (EPU) indices for stock-market returns. The findings suggest that certain categorical EPU indices outperform the original EPU index and popular predictors in predicting stock returns, achieving higher realized utility. Moreover, diffusion indices based on EPU categories, particularly those utilizing partial least squares (PLS) to extract principal components, effectively utilize forecast information from categorical EPU indices, resulting in improved forecast performance, reduced errors, and increased economic value for investors. Additionally, categorical EPU indices demonstrate superior forecasting performance during economic expansions, the China-US trade war, and the COVID-19 pandemic.