Abstract
Institutional investors often need accurate forecasts of yearly stock market returns to advise clients, rebalance portfolios or implement active asset allocation decisions. Traditional macroeconomic variables are of little use for predicting short-horizon returns such as a year. We show that a simple model that incorporates interactions between sentiment-related factors provide more accurate forecasts of market returns than the best traditional macroeconomic variable. Predictive regression and stochastic dominance tests show that this result holds both in and out of sample.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have