Realized Intraday Skewness as an A-Share Stock Selection Factor

Summary

This research summary explores whether statistics computed from intraday stock data can add new signals to established multi-factor selection approaches in China’s A-share market. It evaluates realized volatility, realized skewness, and realized kurtosis as candidate factors. The reported tests find little separation in subsequent stock returns for realized volatility and kurtosis, while realized skewness shows more meaningful differentiation across the overall market and the CSI 500 universe. The summary reports negative information coefficients and historical long-portfolio and benchmark-hedged performance figures for those universes.

These results are presented as backtest evidence from the period beginning in 2007, not proof of a durable live-trading edge. The source is a short summary of a research report; it omits factor construction details, portfolio formation and rebalancing rules, transaction costs, data treatment, and robustness checks. The reported skewness relationship is negative, so implementation would need to preserve the tested signal direction. The findings are specific to the stated Chinese equity universes and historical sample and may not generalize to other markets or future conditions.

Key ideas

• The study tests realized volatility, skewness, and kurtosis derived from intraday stock data.
• Realized skewness is reported to distinguish returns in the broad market and CSI 500 universe.
• Realized volatility and kurtosis show little return separation in the reported tests.
• The reported skewness information coefficients are negative, so the tested signal direction matters.
• The summary omits implementation details and does not establish out-of-sample or live performance.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.