Forecasting Stock Returns Using First Half An Hour Order Imbalance

We explore the predictive power of the first half-hour order imbalance (FOIB) to stock returns in Chinese stock market. Our results show thatFOIBpredicts returns better than daily order imbalance both in-sample and out-of-sample. The predictive power ofFOIBis both statistically and economically significant. Moreover, we provide evidence that the predictive power ofFOIBappears stemming from large trade size.