Ask a quant to show you their Sharpe ratio and they'll beam like a proud parent at a school recital. Ask them whether they've adjusted for autocorrelation in their monthly returns and watch the smile flicker. This question matters enormously because a strategy can look statistically bulletproof while hiding a structural flaw that quietly flatters every performance metric you trust.
The direct answer is this: when your monthly returns are positively serially correlated — meaning a good month tends to follow a good month — the standard deviation of those returns is artificially compressed. A lower standard deviation pumps up your Sharpe ratio mechanically, with no improvement in actual risk-adjusted performance. Andrew Lo's landmark 2002 Journal of Finance paper quantified exactly how large this distortion can be, showing some hedge fund Sharpe ratios were overstated by 65% or more once autocorrelation was properly accounted for.
Think of it like measuring your driving speed using only photos taken every hour. If traffic is smooth and consistent, the average looks great — calm, controlled, impressive. But you've lost all the volatility that happened between shots. Monthly NAV reporting in illiquid strategies does the same thing: it smooths the bumps, makes variance look low, and your Sharpe ratio absorbs the compliment without deserving it.
The practical fix is Lo's autocorrelation-adjusted Sharpe, which scales the standard ratio by a correction factor built from the first several lags of your return series' serial correlation. Run a simple Ljung-Box test on your monthly returns first — if you see statistically significant autocorrelation at lag one or two, your reported Sharpe deserves immediate suspicion. Strategies using illiquid assets, smooth mark-to-model pricing, or infrequent rebalancing are the usual suspects. For deeper reading on the mechanics, Investopedia's Sharpe ratio explainer covers the base formula clearly, while Wikipedia's autocorrelation article walks through the statistical structure, and the Ljung-Box test entry gives you the diagnostic tool to apply immediately.
Pull your strategy's monthly return series today, run a lag-1 autocorrelation check, and if the coefficient sits above 0.1 with statistical significance, recalculate using Lo's adjusted formula before you show that Sharpe to anyone.
A Sharpe ratio built on autocorrelated returns isn't a performance metric — it's a polished illusion wearing performance's clothes.
This content is for educational purposes only and does not constitute financial product advice. Past performance is not indicative of future results. Profit Logic Ltd (ACN 688 669 936) accepts no responsibility for errors or omissions in this content or anywhere on this website. Always seek advice from a licensed financial adviser before making investment decisions.