VaR, Smoothing, Liquidity Risk, and Risk Aggregation

Consider a hypothetical fund-of-funds that reports 4.8% five-year volatility on a book with material equity long/short exposure. An allocator tests the return series and finds first-order autocorrelation of 0.38. That reading is consistent with smoothing in the underlying holdings, but autocorrelation alone does not prove it. Suppose a first-order model fits and the excess return is unchanged. Unsmoothing then puts estimated volatility near 7.2%, and the estimated Sharpe falls from 1.4 to roughly 0.94.

Three specialized terms for futures account levels. Futures contracts have no single clear measure of value, so the CTA industry uses three account-level terms:

• Trading level is the account size you and the CTA agree will be traded. It sets position sizes for the CTA's leverage target, serves as the base for management and...
• Funding level is the cash or collateral you actually deposit to back that trading level. It can never fall below the combined margin the exchanges require on the positions.
• Notional funding is the added exposure above the funding level, letting an investor lever an account to a higher trading level than cash funding alone allows.

Common mistakes

• Confusing trading level, funding level, and notional funding. Trading level is the denominator for returns and fees; funding level is cash posted; notional level is the lever in between. Trap: treating the funding level as the trading level hides the leverage in a partly funded account.
• Mixing up the full and short-horizon VaR forms, or using the wrong critical value. Dropping μ is an accepted approximation only when the question allows it; keep μ when the stem supplies it for the full form. At 95% the critical value is −1.6448, not −2.33. Trap: a 95% answer computed with −2.33 overstates VaR.
• Confusing the decay parameter α with the autocorrelation ρ. In the price-lag model $\alpha = 1 - \rho$. Higher $\rho$ means heavier smoothing and a smaller $\alpha$. Trap: swapping α and ρ applies the wrong adjustment. Taking the reciprocal of the volatility multiplier is a separate error, and that one wrongly pushes unsmoothed vol below the reported figure.

Bottom line

• Trading Level = Funding Level + Notional Level; notional funding is cheap implicit leverage, daily settlement creates financing needs and costs, and collateral interest counts in total return. CaR sums the loss if every stop fires at once.
• Parametric VaR = $(\alpha \cdot \sigma) + \mu$ for an unchanged portfolio, with μ often ignored over short horizons; report the negative quantile as a positive loss. Variance can be equal- or exponentially-weighted (λ).
• The omega ratio = upper partial moment / lower partial moment, with a target suited to the product and matched to the return frequency.
• Unsmoothing runs in three steps: $\hat{\rho}$ correlates returns with their one-period lags (T − 1 pairs), then $R_{true} = (R_{reported} - \rho R_{-1})/(1-\rho)$; prices use $P_{true} = P_{-1} + \Delta P_{reported}/\alpha$.

Exam shortcut

When a vignette gives reported vol on illiquid funds, check that smoothing is plausible and a first-order model fits, then apply $\text{True Vol} = \text{Smoothed Vol} \times \sqrt{(1+\rho)/(1-\rho)}$ and carry the estimated unsmoothed figures through every Sharpe, VaR, beta, or optimization step. DECISION: For a normal, liquid linear book with a short horizon, use equal-weight parametric VaR, and ignore μ when the question permits a negligible-mean approximation; otherwise retain μ.

The full lesson (about 8,608 words, 57 min read) adds 2 worked examples, all 4 common mistakes, a self-check, free in the app.

Learning objectives

• alpha systematic risk
• portfolio options
• delta hedging
• delta hedging observations
• mean reversion diversification
• hierarchy alpha
• types alpha
• risk premia betas
• manufactured alpha evidence
• benchmarking attribution overview
• single factor benchmarking
• multifactor benchmarking
• alt asset benchmarking
• benchmarking commodities
• benchmarking managed futures
• benchmarking pe
• peer group benchmarks
• benchmarking re
• margin collateral
• var managed futures
• other liquidity methods
• smoothed returns
• modeling smoothing
• unsmoothing hypothetical
• unsmoothing re data
• risk measurement overview
• risk aggregation
• info categories
• data freq daily weekly monthly
• data freq quarterly annual
• cybersecurity
• risk mgmt structure process

Browse all free CAIA Level II lessons or jump into free CAIA Level II practice questions.