The complementary role of cross-sectional and time-series information in forecasting stock returns
Australian Journal of Management
Published online on June 19, 2015
Abstract
While linear time-series models, technical analysis, and momentum models all extract information from past market data, they each interpret data differently. We test the informative role of three representative models and examine the trading performance of a combined forecasting model at the individual stock level. Our results indicate that these models all contain marginal information and complement each other. The combined trading model captures higher upward trending returns and provides the same downward trending returns compared with the buy-and-hold strategy.