# Garman-Klass Volatility Factor (JP All Stocks)

- **Slug**: `garman-klass-vol-jp-all`
- **Verdict**: marginal (no_edge)
- **Asset class**: equity
- **Categories**: anomaly, factor, volatility
- **Source**: qbuntu-analysis (computed asof 2026-07-30T01:20:51)
- **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/garman-klass-vol-jp-all
- **JSON**: https://qbuntu.ai/v1/strategies/garman-klass-vol-jp-all
- **License**: CC-BY-4.0

## Hypothesis

Garman & Klass (1980): OHLC-based volatility estimator. Testing low-volatility anomaly using GK vol on the full Japanese stock universe.

## Why it didn't work

Across 160 grid combinations, median Sharpe=0.10, best=1.17. Primary failure mode: no_edge.

## Performance summary

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

| Metric | Value |
|---|---|
| Sharpe (median) | 0.0956 |
| Max drawdown | -21% |
| p-value | 0.7 |
| Backtest period | 2022-02-01 to 2026-02-02 |

Sharpe distribution across 160 grid runs: median 0.1, best 1.17 (best-case — not representative), worst -0.72, p25 -0.06, p75 0.28.

## 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 all listed (Prime/Standard/Growth), ~3747 stocks

## Runs (30)

| run_id | params | sharpe | UP | FLAT | DOWN |
|---|---|---:|---:|---:|---:|
| `r-garman-klass-vol-jp-all-0000` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=1 | 0.01 | -1.45 | 0.64 | -0.3 |
| `r-garman-klass-vol-jp-all-0001` | cost_bps=5, n_stocks=5, regime_gate=true, holding_days=1 | 0.51 | 0.17 | 0.64 | -0.3 |
| `r-garman-klass-vol-jp-all-0002` | cost_bps=10, n_stocks=5, regime_gate=false, holding_days=1 | -0.19 | -1.61 | 0.42 | -0.5 |
| `r-garman-klass-vol-jp-all-0003` | cost_bps=10, n_stocks=5, regime_gate=true, holding_days=1 | 0.29 | -0.04 | 0.42 | -0.5 |
| `r-garman-klass-vol-jp-all-0004` | cost_bps=5, n_stocks=10, regime_gate=false, holding_days=1 | -0.39 | -2.6 | 0.28 | -2.14 |
| `r-garman-klass-vol-jp-all-0006` | cost_bps=10, n_stocks=10, regime_gate=false, holding_days=1 | -0.72 | -2.94 | -0.06 | -2.72 |
| `r-garman-klass-vol-jp-all-0019` | cost_bps=10, n_stocks=5, regime_gate=true, holding_days=5 | 0.45 | 1 | 0.41 | -0.55 |
| `r-garman-klass-vol-jp-all-0033` | cost_bps=5, n_stocks=5, regime_gate=true, holding_days=10 | 0.23 | 1.24 | 0.19 | -2.05 |
| `r-garman-klass-vol-jp-all-0039` | cost_bps=10, n_stocks=10, regime_gate=true, holding_days=10 | 0.04 | 0.58 | 0.18 | -3.58 |
| `r-garman-klass-vol-jp-all-0053` | cost_bps=5, n_stocks=10, regime_gate=true, holding_days=20 | 0.32 | -0 | 0.44 | -0.33 |
| `r-garman-klass-vol-jp-all-0064` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=60 | 0.09 | 0.14 | 0.08 | 0.07 |
| `r-garman-klass-vol-jp-all-0068` | cost_bps=5, n_stocks=10, regime_gate=false, holding_days=60 | 0.21 | 0.24 | 0.09 | 1.64 |
| `r-garman-klass-vol-jp-all-0082` | cost_bps=10, n_stocks=5, regime_gate=false, holding_days=1 | -0.25 | -2.06 | 0.57 | -0.71 |
| `r-garman-klass-vol-jp-all-0096` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=5 | -0.06 | -1.46 | 0.69 | -0.55 |
| `r-garman-klass-vol-jp-all-0102` | cost_bps=10, n_stocks=10, regime_gate=false, holding_days=5 | -0.32 | -1.83 | 0.33 | -0.91 |
| `r-garman-klass-vol-jp-all-0116` | cost_bps=5, n_stocks=10, regime_gate=false, holding_days=10 | 0.02 | 0.17 | 0.17 | -2.39 |
| `r-garman-klass-vol-jp-all-0130` | cost_bps=10, n_stocks=5, regime_gate=false, holding_days=20 | -0.31 | -0.54 | -0.16 | -1 |
| `r-garman-klass-vol-jp-all-0144` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=60 | 0.07 | 0.44 | -0.07 | 0.27 |
| `r-garman-klass-vol-jp-all-0150` | cost_bps=10, n_stocks=10, regime_gate=false, holding_days=60 | -0.03 | 0.39 | -0.21 | -0.07 |
| `r-garman-klass-vol-jp-all-0161` | cost_bps=5, n_stocks=5, regime_gate=true, holding_days=1 | 1.17 | 0.14 | 1.49 | 0.42 |
| `r-garman-klass-vol-jp-all-0165` | cost_bps=5, n_stocks=10, regime_gate=true, holding_days=1 | 0.61 | -0.63 | 0.99 | 0.51 |
| `r-garman-klass-vol-jp-all-0179` | cost_bps=10, n_stocks=5, regime_gate=true, holding_days=5 | 0.75 | 1.36 | 0.66 | 0.59 |
| `r-garman-klass-vol-jp-all-0193` | cost_bps=5, n_stocks=5, regime_gate=true, holding_days=10 | 0.75 | 2.01 | 0.84 | -3.56 |
| `r-garman-klass-vol-jp-all-0199` | cost_bps=10, n_stocks=10, regime_gate=true, holding_days=10 | 0.19 | 0.8 | 0.05 | -0.4 |
| `r-garman-klass-vol-jp-all-0213` | cost_bps=5, n_stocks=10, regime_gate=true, holding_days=20 | 0.14 | 0.86 | -0.07 | 1.11 |
| `r-garman-klass-vol-jp-all-0227` | cost_bps=10, n_stocks=5, regime_gate=true, holding_days=60 | 0.11 | 2.5 | -0.13 | -2 |
| `r-garman-klass-vol-jp-all-0240` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=1 | 0.24 | -1.74 | 1.27 | 0.18 |
| `r-garman-klass-vol-jp-all-0242` | cost_bps=10, n_stocks=5, regime_gate=false, holding_days=1 | 0.04 | -1.89 | 1.01 | 0.05 |
| `r-garman-klass-vol-jp-all-0256` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=5 | -0.15 | -1.35 | 0.48 | 0.34 |
| `r-garman-klass-vol-jp-all-0262` | cost_bps=10, n_stocks=10, regime_gate=false, holding_days=5 | -0.23 | -1.39 | 0.24 | 0.51 |

## Facts (5)

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

- **Best grid Sharpe ratio is 1.17 (p=0.021).**
  - Value: 1.17 sharpe_ratio
  - Context: period 2022-02-01–2026-02-02; cost=5bps
  - Supports verdict: `marginal`
  - Cite: https://qbuntu.ai/cite/garman-klass-vol-jp-all-fact-best-sharpe

- **Median Sharpe across 160 grid runs is 0.10.**
  - Value: 0.1 sharpe_ratio
  - Context: Full grid of 160 parameter combinations.
  - Supports verdict: `marginal`
  - Cite: https://qbuntu.ai/cite/garman-klass-vol-jp-all-fact-median-sharpe

- **Median Sharpe in DOWN regime is -0.52 across 160 runs.**
  - Value: -0.52 sharpe_ratio
  - Context: Regime=DOWN, N225 SMA20/SMA60 classification.
  - Supports verdict: `marginal`
  - Cite: https://qbuntu.ai/cite/garman-klass-vol-jp-all-fact-regime-down

- **Median Sharpe in FLAT regime is 0.22 across 160 runs.**
  - Value: 0.22 sharpe_ratio
  - Context: Regime=FLAT, N225 SMA20/SMA60 classification.
  - Supports verdict: `marginal`
  - Cite: https://qbuntu.ai/cite/garman-klass-vol-jp-all-fact-regime-flat

- **Median Sharpe in UP regime is 0.18 across 160 runs.**
  - Value: 0.18 sharpe_ratio
  - Context: Regime=UP, N225 SMA20/SMA60 classification.
  - Supports verdict: `marginal`
  - Cite: https://qbuntu.ai/cite/garman-klass-vol-jp-all-fact-regime-up

## Related strategies

- same_strategy: [garman-klass-vol-jp-growth](https://qbuntu.ai/strategies/garman-klass-vol-jp-growth)

---

Cite as: qbuntu (2026). Garman-Klass Volatility Factor (JP All Stocks). https://qbuntu.ai/strategies/garman-klass-vol-jp-all

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