Abstract: | In this article we reexamine the profitability of technicalanalysis using Whites reality check and HansensSPA test that correct the data snooping bias. Compared to previousstudies, we study a more complete "universe" of trading techniques,including not only simple rules but also complex trading strategies,and we test the profitability of these rules and strategieswith four main indices. It is found that significantly profitablesimple rules and complex trading strategies do exist in thedata from relatively "young" markets (NASDAQ Composite and Russell2000) but not in the data from relatively "mature" markets DowJones Industrial Average (DJIA) and S&P 500]. Moreover,after taking transaction costs into account, we find that thebest rules for NASDAQ Composite and Russell 2000 outperformthe buy-and-hold strategy in most in- and out-of-sample periods.It is also found that complex trading strategies are able toimprove on the profits of simple rules and may even generatesignificant profits from unprofitable simple rules. |