A conversation with Claude Opus 4
The compact formula for daily option P&L that relates realized variance to implied variance is:
Daily P&L ≈ ½ × Vega × (σ²_realized – σ²_implied) × Δt
Where:
This formula comes from the fact that options are essentially a bet on variance, and the P&L approximately equals half the vega times the difference between realized and implied variance.
For a more precise version that includes gamma effects:
Daily P&L ≈ ½ × S² × Gamma × (σ²_realized – σ²_implied) × Δt
Where:
This relationship is fundamental to volatility trading and shows why:
The factor of ½ appears because the gamma P&L from hedging accumulates continuously and represents the average exposure over the period.
Let’s work through this step-by-step with a 20-day delta-hedged 0.50 delta call option.
Given:
Step 1: Calculate the realized variance
Step 2: Calculate the implied variance (daily)
Step 3: Estimate gamma For an ATM option with 20 days to expiry:
Step 4: Calculate the P&L Using the formula: P&L = ½ × S² × Gamma × (σ²_realized – σ²_implied) × Δt
P&L = ½ × (100)² × 0.028 × (0.0004 – 0.0001016) × 1 P&L = ½ × 10,000 × 0.028 × 0.0002984 P&L = 140 × 0.0002984 P&L ≈ $0.042 per share
Interpretation: The position made about 4.2 cents per share because the realized variance (4 basis points) was much higher than the implied variance (1.016 basis points). The 2% move in one day represents about 32% annualized volatility, which is double the 16% implied volatility, leading to a profit for the long volatility position.
Let’s compute the P&L by breaking it down into gamma P&L and theta P&L separately.
Gamma P&L Calculation: For a delta-hedged position, gamma P&L = ½ × Gamma × S² × (ΔS/S)²
Theta P&L Calculation: For an ATM option with 20 days to expiry:
Total P&L = Gamma P&L + Theta P&L
Comparison:
Why the difference? The discrepancy of ~$0.031 comes from:
The variance-based formula is generally more accurate for volatility trading analysis because it directly captures the essence of the trade: you’re long/short variance, not just gamma and theta separately.
Let’s recalculate with a 1% move instead of 2%.
Given (updated):
Variance-Based Formula:
Step 1: Calculate realized variance
Step 2: Daily implied variance (unchanged)
Step 3: Calculate P&L
Gamma + Theta Approach:
Gamma P&L:
Theta P&L (unchanged):
Total P&L:
Comparison:
Key Insights:
This demonstrates why the variance-based approach is superior for understanding volatility trading – it directly answers “did volatility exceed expectations?”
Yes, exactly! The gamma + theta approach is the discrete approach.
Discrete Approach (Gamma + Theta):
Continuous Approach (Variance-based):
The key difference is that the variance formula emerges from the continuous hedging limit, where you’re constantly rebalancing your delta hedge. In this limit:
Why the variance formula is more accurate:
The discrete approach is useful for understanding the mechanics, but the variance approach better represents the true economics of volatility trading.
For the discrete method, the total option P&L from 20 DTE until expiry is the summation:
Total P&L = Σᵢ₌₁ⁿ [½ × Gammaᵢ × S²ᵢ × (ΔSᵢ/Sᵢ)² – Thetaᵢ × Δt]
Where:
Expanded form with Greek evolution: Since gamma and theta change as the option approaches expiry:
Total P&L = Σᵢ₌₁²⁰ [½ × Gamma(Sᵢ, σ, Tᵢ) × S²ᵢ × (ΔSᵢ/Sᵢ)² – Theta(Sᵢ, σ, Tᵢ) × (1/252)]
Where Tᵢ = (20-i+1)/252 is the time to expiry at step i.
For an initially ATM option, the Greeks evolve roughly as:
At expiry: The final P&L also includes the intrinsic value:
This discrete summation becomes increasingly inaccurate for:
Let’s run this scenario where the stock resets to $100 each day after a 1% move, rolling forward for 20 days.
Setup:
Daily Calculations:
For each day i (where i goes from 20 DTE down to 1 DTE):
Let me calculate key days:
Day 1 (20 DTE):
Day 10 (11 DTE):
Day 15 (6 DTE):
Day 19 (2 DTE):
Total Cumulative P&L ≈ Σ(daily P&L) ≈ -$0.90 to -$1.00
Key Insights:
This artificial scenario highlights the limitation of discrete hedging analysis!
You’re absolutely right! This is a critical point. Let me recalculate the last day.
Day 20 (1 DTE → Expiry):
But here’s the key issue:
Final day P&L:
Total final day P&L ≈ -$0.64 (much worse than other days!)
This illustrates a crucial point about gamma trading near expiry:
This makes the total 20-day cumulative loss even larger than my initial estimate – probably closer to -$1.40 to -$1.50 total.
You’re absolutely correct! I made an error in my logic. Let me recalculate properly.
Day 20 (1 DTE → Expiry):
P&L breakdown:
But we still have:
So the final day P&L is just the theta: -$0.20
This makes much more sense! The delta hedge is doing exactly what it should – protecting against directional moves. We only lose the time decay.
Revised total 20-day cumulative P&L: Since we lose roughly the daily theta each day, and theta increases as we approach expiry, the total loss would be approximately the initial option premium (around -$1.00 to -$1.20).
This aligns with the intuition that if realized vol = implied vol, we should lose approximately the option premium over the life of the trade through theta decay, with gamma gains offsetting the acceleration of theta near expiry.
Thanks for catching that error!
You’re absolutely right! On the final day, there’s no theta decay because the option expires that day.
Day 20 (Final day):
P&L breakdown:
There’s no theta on expiration day – the option just settles at intrinsic value!
This actually makes the scenario even more interesting:
The cumulative P&L would be the sum of losses from days 1-19 only, which would be somewhat less than my previous estimate – probably around -$0.80 to -$0.90 total.
This highlights another key concept: on expiration day, options become pure directional instruments with no time value, so a delta hedge works perfectly with no slippage from theta.
You’re right to be suspicious! Let’s carefully track the option value and hedge P&L each day. The key is that we need to track:
Let me recalculate Day 1 properly:
Day 1 (20 DTE → 19 DTE):
P&L breakdown:
Wait, this is different from our gamma/theta calculation!
The issue is that the option value change includes:
Let me recalculate using actual option pricing:
The -$0.05 loss makes sense because:
Should we work through a few more days this way to see the pattern?
Let me calculate Day 1 (going from 20 DTE to 19 DTE) using Black-Scholes values:
Day 1: 20 DTE → 19 DTE
Starting position:
After 1% move:
P&L calculation:
What happened:
After the reset to $100 for next day, we’d rehedge to the new 19 DTE delta of ~0.51.
This shows why the discrete hedging approach systematically loses money even when realized = implied!
I’ll run through all 20 days, repricing the option each day. Let me calculate key milestone days:
Day 1: 20 DTE → 19 DTE
Day 5: 16 DTE → 15 DTE
Day 10: 11 DTE → 10 DTE
Day 15: 6 DTE → 5 DTE
Day 19: 2 DTE → 1 DTE
Day 20: 1 DTE → Expiry
Total Cumulative P&L: Summing all 20 days ≈ -$2.20
Key observations:
Why so much loss?
In reality, stock prices follow continuous paths, which is why the variance formula (showing near breakeven) better represents actual trading outcomes.
The continuous hedging P&L formula is derived from the Black-Scholes PDE and Ito’s lemma. Here’s the key derivation:
Starting point: Black-Scholes PDE For a hedged portfolio (long option, short Δ shares):
∂V/∂t + ½σ²S²(∂²V/∂S²) + rS(∂V/∂S) - rV = 0 Key insight: The P&L from continuous delta hedging comes from two sources:
Step-by-step derivation:
dV = (∂V/∂t)dt + (∂V/∂S)dS + ½(∂²V/∂S²)(dS)² dV = (∂V/∂t)dt + ΔSμdt + ΔσSdW + ½Γσ²S²dt dΠ = dV - ΔdS
= (∂V/∂t)dt + ½Γσ²S²dt ∂V/∂t = -½σ²S²Γ - rSΔ + rV dΠ = -½σ²S²Γdt + ½Γσ²S²dt
= ½ΓS²(σ²_realized - σ²_implied)dt The key transformation: Over time period T:
∫₀ᵀ ½ΓS²(σ²_realized - σ²_implied)dt ≈ ½Vega(σ²_realized - σ²_implied)T This approximation works because:
Final formula:
P&L ≈ ½ × Vega × (σ²_realized - σ²_implied) × T Intuition:
This formula assumes continuous rehedging, which is why it differs from discrete hedging calculations!
Euan Sinclair needs no introduction from me. I’ll cut straight to the gold. He’s been…
A moontower user sent this [paraphrased] message in our Discord the morning of Jan 9th:…
Remember that chart of CAR last week. (Matt Levine wrote about the fundamentals of the squeeze on…
At least once a day, I think about how the staunchest supporters of “broken window…
From @buccocapital on Anthropic CEO’s insistence that AI is going to wipe out 50% of jobs. Bingo.…
In this issue: obvious error rule broken window theory why home prices aren’t going to…