Mixed Interval Realized Variance : A Robust Estimator of Stock Price Volatility

This paper proposes an ex post volatility estimator, called mixed interval realized variance (MIRV), that uses high-frequency data to provide measurements robust to the idiosyncratic noise of stock markets caused by market microstructures. The theoretical properties of the new volatility estimator are illustrated and compared with those of the two currently dominant realized measures: realized volatility and realized range. A simulation study adds to this comparison and highlights some favorable robustness properties of the new estimator when subject to market microstructures. The main finding is that mixed interval realized variance is robust to the presence of microstructures, being superior to realized volatility and realized range in several circumstances, but inconsistent in the hypothetical ideal scenario. The empirical study features Australian stocks from the ASX 20 and provides evidence that the mixed interval realized variance is competitive with other realized measures via several measures, including predictive likelihood when it is included in a Realized GARCH model