E-05. Sizing A/B + Monte Carlo (2026-07-09)
| Option | Return | Sharpe | MDD | P(MDD≤-15%) |
|---|---|---|---|---|
| A 50%×2 | 93.7% | 1.20 | -18.8% | 92.9% |
| B 25%×2 | 42.5% | 1.22 | -9.4% | 19.4% |
| C vol target | 83.3% | 1.25 | -16.6% | 83.5% |
| D drawdown reduction | 92.2% | 1.19 | -19.8% | 92.9% |
| E C+D | 81.0% | 1.23 | -17.4% | 83.8% |
| F 25%×2 + vol target | 36.4% | 1.25 | -8.5% | 12.6% |
- Analysis: sizing barely changes Sharpe (1.19~1.25) and only scales drawdown. D (reducing after the fact) cannot prevent a kill breach — discarded. F adopted (D-007). Monte Carlo reshuffles observations, so it is an optimistic lower bound.
Source and migration evidence
Source: backtest/docs/experiment-log.md#E-05
Original SHA-256: 069c4aaaf53a20930ca8d94ba6365b4ce2b6bc560171d662a4c179ea55a6857c
Raw data and account information are not part of the public package. The original results do not replace statistical or scientific revalidation. The English text is a translation; numbers, tables and charts are carried over unchanged.