Working Paper Internal working draft · 2026
Bayesian Parameter Uncertainty in WTI Average Price Option Valuation
Summary
A working study of Bayesian parameter uncertainty in WTI average-price option valuation. It separates statistical learning under the physical measure from no-arbitrage valuation under the risk-neutral measure and propagates posterior uncertainty in volatility into arithmetic-average option prices. The empirical design combines \(213\) unique call and put contracts with \(11{,}179\) option-date observations spanning September 2026 to June 2029.
$$ \theta=(\mu,\sigma) $$
Context
The paper studies CME WTI Average Price Options and asks when posterior parameter uncertainty becomes material as maturity, moneyness, posterior dispersion, and oil-market volatility change. The draft keeps its pricing results explicitly preliminary and internal.
Main contributions
- Separates statistical learning under the physical measure from no-arbitrage valuation under the risk-neutral measure.
- Evaluates posterior integration and posterior-mean plug-in pricing in repeated-sampling experiments where the true risk-neutral price is known.
- Applies the framework to CME WTI Average Price Options using 213 unique call and put contracts and 11,179 option-date observations.
- Respects the calendar-month average of first-nearby WTI futures settlements and distinguishes realized from remaining fixings.