Profits from Technical Trading Rules
比较了两种技术交易规则在道琼斯工业平均指数日收益率上的预测效果，发现看似成功的移动平均规则可能是数据挖掘的虚假结果，提醒历史模式未必能持续。
I examine the predictability of daily returns for the Dow Jones Industrial Average by comparing the technical trading rules developed by Allen and Karjalainen (1999) with moving average rules studied by Brock, Lakonishok, and LeBaron (1992). I argue that this comparison lends support to the hypothesis that the apparent success (after transaction costs) of the Brock et al. (1992) moving average rules is a spurious result of data snooping. If it were reliable, investors would like to use technical analysis to improve their portfolio returns, and firms would like to use it to improve the timing of their security offerings. My results serve as a reminder that patterns in historical data, even though they appear very consistent, need not persist in the future.