A Market Microstructure Explanation for Predictable Variations in Stock Returns following Large Price Changes
发现股票大额价格变动后的收益可预测变化部分源于买卖价差内收盘价系统移动导致的样本选择偏差，控制后短期反转仍存在，但套利利润不足以覆盖交易成本。
Prior empirical evidence of predictable variations in stock returns following large price changes is found to be, at least in part, driven by the sample selection bias arising from the systematic movement of closing transaction prices within the bid-ask spread. By using the average of the bid-ask prices in the sample selection process, the price reversal on the day following the events (day +1) disappears. For a short-run period after day +1, however, systematic abnormal return patterns are still observed. These short-run price reversals persist even after controlling for the influence of systematic trading patterns around the events. However, investigation of contrarian investment profits from these short-run price reversals shows that the average abnormal returns are not large enough to cover the transaction price movement between the bid and ask prices.