# Skewness Anomaly (JP Growth Stocks)

- **Slug**: `skewness-anomaly-jp-growth`
- **Verdict**: rejected (no_edge)
- **Asset class**: equity
- **Categories**: anomaly, factor, lottery, skewness
- **Source**: qbuntu-analysis (computed asof 2026-08-01T07:31:30)
- **Reproducibility**: analysis-engine@18193e9, backtest-lib@711b855, grid tier=shallow (python 3.10.11, numpy 2.2.6, pandas 2.3.3)
- **HTML**: https://qbuntu.ai/strategies/skewness-anomaly-jp-growth
- **JSON**: https://qbuntu.ai/v1/strategies/skewness-anomaly-jp-growth
- **License**: CC-BY-4.0

## Hypothesis

Boyer, Mitton, Vorkink (2010): stocks with high expected skewness earn lower returns as investors overpay for lottery-like payoffs. LONG lowest skew, SHORT highest skew.

## Why it didn't work

Across 320 grid combinations, median Sharpe=-0.42, best=0.57. Primary failure mode: no_edge.

## Performance summary

Headline figures are the **median across the parameter grid**, not the best run.

| Metric | Value |
|---|---|
| Sharpe (median) | -0.4249 |
| Max drawdown | -21.6% |
| p-value | 0.35 |
| Backtest period | 2022-02-01 to 2026-06-01 |

Sharpe distribution across 320 grid runs: median -0.42, best 0.57 (best-case — not representative), worst -1.58, p25 -0.68, p75 -0.14.

## Methodology

- Notes: {"walk_forward_definition": {"type": "single_pass", "description": "Full period backtest without walk-forward split", "verdict_basis": "full_period"}}
- Slippage model: open-on-open + variable bps fixed
- Position sizing: equal_weight
- Regime definition: N225 SMA20/SMA60 three-class
- Transaction cost bps: 5

## Target universe

Tokyo Stock Exchange Growth Market, ~495 stocks, tv >= 30M JPY

## Runs (30)

| run_id | params | sharpe | UP | FLAT | DOWN |
|---|---|---:|---:|---:|---:|
| `r-skewness-anomaly-jp-growth-0000` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=1 | -0.25 | 0.79 | -0.68 | 3.48 |
| `r-skewness-anomaly-jp-growth-0001` | cost_bps=5, n_stocks=5, regime_gate=true, holding_days=1 | -0.44 | -0.1 | -0.68 | 3.48 |
| `r-skewness-anomaly-jp-growth-0002` | cost_bps=10, n_stocks=5, regime_gate=false, holding_days=1 | -0.44 | 0.55 | -0.85 | 3.09 |
| `r-skewness-anomaly-jp-growth-0003` | cost_bps=10, n_stocks=5, regime_gate=true, holding_days=1 | -0.62 | -0.25 | -0.85 | 3.09 |
| `r-skewness-anomaly-jp-growth-0012` | cost_bps=5, n_stocks=50, regime_gate=false, holding_days=1 | -0.51 | -1.13 | -0.2 | -1.03 |
| `r-skewness-anomaly-jp-growth-0018` | cost_bps=10, n_stocks=5, regime_gate=false, holding_days=5 | -0.18 | 1.22 | -0.79 | 1.12 |
| `r-skewness-anomaly-jp-growth-0032` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=10 | -0.24 | 1.21 | -0.74 | -1.05 |
| `r-skewness-anomaly-jp-growth-0046` | cost_bps=10, n_stocks=50, regime_gate=false, holding_days=10 | -0.98 | -2.5 | -0.62 | -3.19 |
| `r-skewness-anomaly-jp-growth-0060` | cost_bps=5, n_stocks=50, regime_gate=false, holding_days=20 | -0.67 | -1.1 | -0.46 | -2.4 |
| `r-skewness-anomaly-jp-growth-0064` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=60 | -0.72 | -0.73 | -0.65 | -2.29 |
| `r-skewness-anomaly-jp-growth-0075` | cost_bps=10, n_stocks=20, regime_gate=true, holding_days=60 | -0.79 | -2.1 | -0.66 | -0.67 |
| `r-skewness-anomaly-jp-growth-0089` | cost_bps=5, n_stocks=20, regime_gate=true, holding_days=1 | -0.1 | -1.12 | 0.09 | 1.83 |
| `r-skewness-anomaly-jp-growth-0103` | cost_bps=10, n_stocks=10, regime_gate=true, holding_days=5 | -0.13 | -0.84 | -0.13 | 3.92 |
| `r-skewness-anomaly-jp-growth-0117` | cost_bps=5, n_stocks=10, regime_gate=true, holding_days=10 | -0.48 | -0.71 | -0.56 | 1.1 |
| `r-skewness-anomaly-jp-growth-0131` | cost_bps=10, n_stocks=5, regime_gate=true, holding_days=20 | -1.19 | -0.16 | -1.39 | -2.28 |
| `r-skewness-anomaly-jp-growth-0134` | cost_bps=10, n_stocks=10, regime_gate=false, holding_days=20 | -1.58 | -1.35 | -1.59 | -2.71 |
| `r-skewness-anomaly-jp-growth-0146` | cost_bps=10, n_stocks=5, regime_gate=false, holding_days=60 | -0.7 | -0.2 | -0.79 | -1.03 |
| `r-skewness-anomaly-jp-growth-0160` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=1 | 0.37 | 0.98 | 0.13 | 1.2 |
| `r-skewness-anomaly-jp-growth-0174` | cost_bps=10, n_stocks=50, regime_gate=false, holding_days=1 | -0.68 | -0.48 | -1.1 | 1.81 |
| `r-skewness-anomaly-jp-growth-0188` | cost_bps=5, n_stocks=50, regime_gate=false, holding_days=5 | 0.06 | 0.59 | -0.49 | 5.73 |
| `r-skewness-anomaly-jp-growth-0202` | cost_bps=10, n_stocks=20, regime_gate=false, holding_days=10 | -0.43 | -0.77 | -0.44 | 1.42 |
| `r-skewness-anomaly-jp-growth-0216` | cost_bps=5, n_stocks=20, regime_gate=false, holding_days=20 | -0.74 | 0.13 | -1.07 | -0.7 |
| `r-skewness-anomaly-jp-growth-0230` | cost_bps=10, n_stocks=10, regime_gate=false, holding_days=60 | -0.81 | -0.63 | -0.94 | 0.43 |
| `r-skewness-anomaly-jp-growth-0240` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=1 | -0.22 | 0.08 | -0.42 | 0.71 |
| `r-skewness-anomaly-jp-growth-0245` | cost_bps=5, n_stocks=10, regime_gate=true, holding_days=1 | 0.13 | -0.27 | 0.19 | 1.62 |
| `r-skewness-anomaly-jp-growth-0259` | cost_bps=10, n_stocks=5, regime_gate=true, holding_days=5 | -0.09 | -0.51 | -0.09 | 2.39 |
| `r-skewness-anomaly-jp-growth-0264` | cost_bps=5, n_stocks=20, regime_gate=false, holding_days=5 | 0.57 | 0.33 | 0.49 | 10.32 |
| `r-skewness-anomaly-jp-growth-0274` | cost_bps=10, n_stocks=5, regime_gate=false, holding_days=10 | -0.29 | -0.82 | -0.16 | 1.58 |
| `r-skewness-anomaly-jp-growth-0288` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=20 | -0.35 | -0.61 | -0.48 | 5.68 |
| `r-skewness-anomaly-jp-growth-0302` | cost_bps=10, n_stocks=50, regime_gate=false, holding_days=20 | -0.68 | -0.79 | -0.92 | 9.56 |

## Facts (5)

Each fact has a permanent citation URL. AI agents quoting qbuntu should use these.

- **Best grid Sharpe ratio is 0.57 (p=0.24).**
  - Value: 0.57 sharpe_ratio
  - Context: period 2022-02-01–2026-06-01; cost=5bps
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/skewness-anomaly-jp-growth-fact-best-sharpe

- **Median Sharpe across 320 grid runs is -0.42.**
  - Value: -0.42 sharpe_ratio
  - Context: Full grid of 320 parameter combinations.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/skewness-anomaly-jp-growth-fact-median-sharpe

- **Median Sharpe in DOWN regime is 0.93 across 320 runs.**
  - Value: 0.93 sharpe_ratio
  - Context: Regime=DOWN, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/skewness-anomaly-jp-growth-fact-regime-down

- **Median Sharpe in FLAT regime is -0.50 across 320 runs.**
  - Value: -0.5 sharpe_ratio
  - Context: Regime=FLAT, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/skewness-anomaly-jp-growth-fact-regime-flat

- **Median Sharpe in UP regime is -0.43 across 320 runs.**
  - Value: -0.43 sharpe_ratio
  - Context: Regime=UP, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/skewness-anomaly-jp-growth-fact-regime-up

---

Cite as: qbuntu (2026). Skewness Anomaly (JP Growth Stocks). https://qbuntu.ai/strategies/skewness-anomaly-jp-growth

Visit qbuntu.ai — the honest scorecard for quant strategies (live, promising, marginal, rejected).