How to use Position Sizing under Edge Variance
Bayesian-Kelly bet sizing when your edge is itself uncertain. The page compares deterministic Kelly, Bayesian-adjusted Kelly, and a conservative lower-bound version so you can see the cost of pretending you know your edge precisely.
What It Does
Use the calculator with intent
Bayesian-Kelly bet sizing when your edge is itself uncertain. The page compares deterministic Kelly, Bayesian-adjusted Kelly, and a conservative lower-bound version so you can see the cost of pretending you know your edge precisely.
Bettors and traders whose edge estimate comes from a small sample and who know they need to size below the in-sample Kelly recommendation.
Interpreting Results
Bayesian-adjusted Kelly is typically 50-70% of deterministic Kelly when sample size is small. Conservative lower-bound is the size that protects against the worst plausible edge in the posterior — use this for the largest bets.
Input Steps
Field by field
- 1
Enter inputs
Enter expected per-trade edge (decimal, e.g., 0.02 = 2%) and standard error of the edge estimate.
- 2
Enter inputs
Enter expected per-trade variance.
- 3
Read outputs
Read the recommended position size as a fraction of capital. Compare against full Kelly (faster growth, less safety) and quarter-Kelly (slower growth, more safety).
- 4
Increase
Increase the edge SE assumption to see how uncertainty erodes recommended size. The sizer is more conservative than Kelly when SE is high.
- 5
Re-run
Re-run as your trade log grows — tighter edge SE estimates allow larger sizes safely.
Common Scenarios
Use realistic starting points
Large sample, well-measured edge
Edge
2%
Sample size
10000 trades
Bayesian and deterministic Kelly nearly identical; uncertainty discount is small. Edge is well-measured.
Small sample, uncertain edge
Edge
5%
Sample size
100 trades
Bayesian Kelly meaningfully below deterministic; conservative bound much smaller. Size to the Bayesian estimate, not the headline number.
Try These Tools
Run the numbers next
Fractional Kelly Sizer
Map conviction tiers to fractional Kelly bet sizes with a drawdown Monte Carlo simulator. Client-side. Private by default.
Drawdown-Recovery Markov Simulator
Time to recover from an N% drawdown given monthly Sharpe + skew + kurtosis. Cornish-Fisher Monte Carlo, percentile distribution of recovery months.
Risk-Adjusted Returns Calculator
Paste a returns CSV. Sharpe, Sortino, Calmar, Omega, alpha, beta, tracking error, information ratio, max drawdown, and tail moments — plus.
FAQ
Questions people ask next
The short answers readers usually want after the first pass.
Related Content
Keep the topic connected
Kelly Criterion
What the Kelly criterion is, when full Kelly blows up, and why most working quants size at half- or quarter-Kelly.
Drawdown
Drawdown explained: peak-to-trough decline, why max drawdown alone is misleading, and the recovery math that actually matters.
Monte Carlo Simulation
Monte Carlo simulation in trading: when it's the right tool, when it's overkill, and the seed-discipline gotcha that ruins most published examples.