Stock return predictability from a mixed model perspective

By Zhifeng Dai, Huan Zhu. 2020

53 citations recorded by the source corpus.

Abstract We find that mixing existing forecasting models can significantly improve prediction performance of stock returns. Empirical results suggest that the stock return forecasting by three proposed mixed models are more significant both in statistical and economic terms than the corresponding models in Campbell and Thompson (2008) , Wang et al. (2018) and Zhang et al. (2019) . This improvement of predictability is also remarkable when we employ the multivariate information to predict stock return. The prediction performance of mixed models is robust to a series of robustness test. Particularly, the three proposed mixed models obtain superior out-of-sample forecasting performance of stock return for business cycles, rolling window predictions and different out-of-sample periods.

Subfields: Economics and Econometrics, Finance, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/2d48f87574a8a7bf9b53a884696f7bc53b44a012