零售交易者的覆灭：流行信号失败剖析
Retail Trader's Ruin: An Anatomy of Popular Signal Failure
浏览论文内容
中文总结 AI 辅助
研究零售交易中五个信号类别能否带来优势，通过多种测试方法判断，六个候选信号中四个被驳斥，趋势和动量校准基准尚无定论，不同场景下存活约束有别，拒绝特定推广主张，将未解决情况分类，而非视非显著性为证据。
中文摘要 AI 辅助
我们测试了五个广泛推广的零售信号类别——趋势、振荡器、蜡烛图、成交量和日历规则——是否能带来积极的、具有经济意义的、成本后净值且可存活的优势。实际可行性由三个预先声明的标准共同决定：多重校正后的统计优势、交易成本后的经济可行性以及杠杆作用下有限资金的存活能力。暴露匹配基准、平稳自举置信区间、分层Benjamini-Yekutieli控制、单边索赔排除测试和等效性测试区分了积极证据、经统计驳斥的重要性和未解决的情况。六个候选信号中的四个——振荡器、成交量、日历和蜡烛图——被驳斥，基于统计和/或经济重要性理由被排除；趋势和一个动量校准基准尚无定论，在此样本量下置信区间过宽无法解决该主张；没有一个得到支持。横截面测试使用时间点成员资格和退市校正。动量基准本身未通过统计标准，被归类为尚无定论，而非被驳斥——这是真正不确定的阳性对照不会被此设计错误证伪的关键有效性特征。在美国主要场景下，在FINRA和ESMA设定的杠杆和保证金场景中，存活并非任何测试信号类别的约束条件，但在更高杠杆的欧盟差价合约场景下，趋势和振荡器信号变得具有区分性。结果拒绝了特定的推广可部署性主张，即置信区间排除了声明的效果阈值，并将其余情况归类为未解决，而不是将非显著性视为证据。
英文摘要
We test whether five widely promoted retail signal families - trend, oscillator, candlestick, volume, and calendar rules - deliver a positive, economically meaningful, net-of-cost, and survivable edge. Practical viability is the conjunction of three predeclared gates: statistical edge after multiplicity correction, economic viability after trading costs, and finite-bankroll survival under leverage. Exposure-matched benchmarks, stationary-bootstrap confidence intervals, hierarchical Benjamini-Yekutieli control, one-sided claim-exclusion tests, and equivalence tests distinguish positive evidence, statistically refuted materiality, and unresolved cases. Four of six candidates - oscillator, volume, calendar, and candlestick - are REFUTED, ruled out on statistical and/or economic materiality grounds; trend and a momentum calibration benchmark are INCONCLUSIVE, with confidence intervals too wide at this sample size to resolve the claim; none is SUPPORTED. Cross-sectional tests use point-in-time membership and delisting corrections. The momentum benchmark itself does not clear the statistical gate and is classified INCONCLUSIVE, not REFUTED - the critical validity signature that a genuinely uncertain positive control is never falsely falsified by this design. Under FINRA- and ESMA-anchored leverage and margin scenarios, survival is not the binding constraint for any tested family at the US headline scenario, though it becomes discriminating for trend and oscillator under the higher-leverage EU CFD scenario. The results reject specific promoted deployability claims where confidence bounds rule out the declared effect threshold and classify the remaining cases as unresolved rather than treating non-significance as proof.
