Assessing Whether a Trading Strategy Has a Genuine Edge
Summary
The article addresses how to distinguish a durable strategy effect from luck, while acknowledging that certainty is impossible. It recommends starting with a credible economic explanation, such as compensation for bearing risk or a structural imbalance in supply and demand. Researchers should then examine whether the effect persists across time, appears in the markets or conditions predicted by the hypothesis, and is absent where the hypothesis says it should not occur.
The author warns that statistical significance can be misleading when many variants were tried before selecting a favorable result, and that a widely recognized effect may be arbitraged away before academic certainty arrives. Diversifying across strategies with different rationales is presented as a way to reduce reliance on any single edge. These are practical guidelines rather than a formal testing protocol: the article supplies illustrative examples and personal experience, but no datasets or comparative performance analysis. Its advice is to combine economic reasoning, direct evidence, diversification, and humility.
Key ideas
- Begin with a plausible reason why another market participant would take the other side of the trade.
- Check whether the observed effect persists and appears in conditions predicted by the hypothesis.
- Look for settings where the effect should be absent as well as settings where it should appear.
- Statistical significance may conceal extensive unreported experimentation or p-hacking.
- Holding strategies based on different edges can reduce the damage when one stops working.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.