What Is HAC Sharpe?
HAC Sharpe is a Sharpe ratio where the denominator is estimated using a Heteroskedasticity and Autocorrelation Consistent (HAC) long-run variance estimator instead of the ordinary sample standard deviation.
It is used in quantitative finance, backtesting and trading strategy research when strategy returns are not independent and identically distributed. This is common when a strategy holds positions for multiple bars, uses rolling signals, trades overlapping portfolios, smooths exposures, or reports high-frequency returns from positions that change more slowly than the reporting interval.
A plain Sharpe ratio can overstate risk-adjusted return when returns are positively autocorrelated, because the usual sample standard deviation does not fully capture serial dependence. HAC Sharpe uses a Newey-West style long-run variance estimate that allows both changing return variance and return autocorrelation. The result is usually a more conservative and more defensible Sharpe estimate for autocorrelated strategy PnL streams.
HAC Sharpe is not automatically “better” in every setting. For simple buy-and-hold returns sampled at a horizon where observations are close to independent, the ordinary Sharpe ratio may be easier to interpret. HAC Sharpe is better when the research question is whether an apparent edge survives more realistic time-series uncertainty.
Literature and references:
Whitney K. Newey and Kenneth D. West, A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix, Econometrica, 1987.
Andrew W. Lo, The Statistics of Sharpe Ratios, Financial Analysts Journal, 2002.
Newey and West, NBER Technical Working Paper version.
See also