The profitability of technical trading rules in United States futures markets

Numerous empirical studies have investigated the profitability of technical trading rules in financial markets, and many found positive profits. Despite positive evidence about profitability and improvements in testing procedures, skepticism about technical trading profits remains widespread among academics mainly due to data snooping problems. When a set of data is repeatedly used to search for "profitable" trading rules, systems, markets, or performance measures, any successful results may be obtained by chance.; The objective of this study is to determine whether technical trading rules have been profitable in US futures markets during the 1985--2004 period after accounting for data snooping problems. Two approaches are used to achieve the objective. The first approach is to confirm the results of an original study and then replicate the procedures on a new body of data. A well-known 1988 study by Lukac, Brorsen, and Irwin is chosen as the original application because they found strong evidence on technical trading profits in 12 US futures markets using comprehensive and carefully documented testing procedures. Despite its usefulness, a replication study is by definition limited to the trading systems and markets analyzed in the original study. In the second approach, additional trading systems and markets are investigated using two data-snooping-adjusted statistical tests: White's (2000) Bootstrap Reality Check methodology and Hansen's (2005) Superior Predictive Ability (SPA) test. These tests are designed to directly quantify the effect of data snooping by evaluating the performance of the best rule in the context of the full universe of technical trading rules.; The results of the first approach confirm Lukac, Brorsen, and Irwin's successful findings during the 1978--1984 period. The replication results, however, show that substantial technical trading profits during the early period disappeared in the subsequent 1985--2003 period. The results of the second approach indicate that the best rule of 14 technical trading systems generates statistically significant economic profits only for 2 of 17 US futures markets over 1985--2004.{09}This evidence suggests that technical trading rules in general have not been profitable in US futures markets over the last 20 years after correcting for data snooping biases.