Technical Analysis and Discrete False Discovery Rate: Evidence from MSCI Indices

Abstract

We investigate the performance of dynamic portfolios constructed using more than 21,000 technical trading rules on 12 categorical and country-specific markets over the 2004-2015 study period, on rolling forward structures of different lengths. We also introduce a discrete false discovery rate (DFRD+/-) method for controlling data snooping bias. Compared to the existing methods, DFRD+/- is adaptive and more powerful, and accommodates for discrete p-values. The profitability, persistence and robustness of the technical rules are examined. Technical analysis still has short-term value in advanced, emerging and frontier markets. Financial stress, the economic environment and market development seem to affect the performance of trading rules. A cross-validation exercise highlights the importance of frequent rebalancing and the variability of profitability in trading with technical analysis.