 No pain, no gain: You should always incorporate trading costs for a bias-free evaluation of trading rule overperformanceEconomics Letters, 2022, vol. 216, issue C Abstract: In their search for better-performing trading rules (forecasting models), traders and researchers always engage in some form of data snooping. In the current context of extensive data snooping efforts, we show that accounting for both transaction fees and liquidity costs is crucial for controlling data snooping bias. Specifically, we document that even state-of-the-art, conservative multiple testing procedures (MTPs) have significant size distortions when either is missing from the loss function that describes trading (over)performance. This result is not obvious as, in theory, MTP results should not depend on how the loss function is specified. However, empirical realities differ from theory in a way that requires traders and researchers to directly consider trading costs when looking to adequately control false discoveries. Keywords: Trading rules; Forecasting models; Trading costs; Data snooping; Multiple testing procedures; False discoveries (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:eee:ecolet:v:216:y:2022:i:c:s0165176522001720 DOI: 10.1016/j.econlet.2022.110584 Access Statistics for this article Economics Letters is currently edited by Economics Letters Editorial Office More articles in Economics Letters from Elsevier |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.