Empirical Finance is in crisis: Our most important discovery tool is historical simulation, and yet, most backtests and time series analyses published in journals are flawed. The problem is well-known to professional organizations of Statisticians and Mathematicians, who have publicly criticized the misuse of mathematical tools among Finance researchers. In this note I point to three problems and propose four practical solutions. In an attempt to overcome the challenges posed by multiple testing and selection bias, I emphasize the need to move from an individual-centric to a community-driven research paradigm. Low retraction rates can be corrected through technologies that derive “peer p-values”. Stronger theoretical foundations and closer ties with financial firms would help prevent false discoveries.
Fonte: Lopez de Prado, Marcos, The Future of Empirical Finance (May 31, 2015). Journal of Portfolio Management, 41(4). Summer 2015.