Risk management for asset managers: A test of relative VaR

Estimating ex ante the potential tracking error of a fund through a Relative VaR measure is an important tool for fund managers. This paper tests the accuracy of Relative VaR and identifies some methodological issues which are extremely important when backtesting them. In particular, while the unconditional accuracy of Relative VaR estimates is high, the assessment of unconditional accuracy is hampered by negative tracking error autocorrelation. The extent of this effect, well known when daily relative returns are used, is shown to be still relevant with weekly data and to decline only on longer time horizons.