We perform a comprehensive examination of the recursive, comparative predictive performance of a number of linear and non-linear models for UK stock and bond returns. We estimate Markov switching, threshold autoregressive (TAR), and smooth transition autoregressive (STR) regime switching models,...

We combine annual stock market data for the most important equity markets of the last four centuries: the Netherlands/U.K. (1629-1812), U.K. (1813-1870) and U.S. (1871-2015). We show that dividend yields are stationary and consistently forecast returns. The documented predictability holds for...

We build an equilibrium model to explain why stock return predictability concentrates in bad times. The key feature is that investors use different forecasting models, and hence assess uncertainty differently. As economic conditions deteriorate, uncertainty rises and investors' opinions...

The empirical literature of stock market predictability mainly suffers from model uncertainty and parameter instability. To meet this challenge, we propose a novel approach that combines the documented merits of diffusion indices, regime-switching models, and forecast combination to predict the...

This paper investigates whether the HML, the SMB along with the short-term reversal, the long-term reversal and the momentum factors exhibit both in-sample and out-of-sample forecasting ability for the US stock returns. Our findings suggest that these factors contain significantly more...

Based on data until the mid 2000s, oil price changes were shown to predict international equity index returns with a negative predictive slope. Extending the sample to 2015, we document that this relationship has been reversed over the last ten years and therefore has not been stable over time....

Using the long-term wavelet component of monthly S&P 500 excess returns as supervision information, we employ a machine learning method to extract the common predictive information of 14 prevalent macroeconomic variables, and construct a new macroeconomic index aligned for predicting stock...

We use a Panel Smooth Transition Regression (STR) model to study nonlinearities in the expectationformation process in the US stock market. To this end, we use data from the Livingston survey to investigate how the importance of regressive and extrapolative expectations fluctuates over time as...