Estimating the integrated volatility of high frequency realized prices is an important issue in microstructure literature. Bandi and Russell (2006) derived the optimal-sampling frequency, and Zhang et al. (2005) proposed a "two-scales estimator" to solve the problem. In this study, we propose a new estimator based on a signal to noise ratio statistic with convergence rate of Op (n^(−1/ 4) ). The method is applicable to both constant and stochastic volatility models and modi¡Âes the Op (n^(−1/ 6) ) convergence rate of Zhang et al. (2005). The proposed estimator is shown to be asymptotic e¡Ócient as the maximum likelihood estimate for the constant volatility case. Furthermore, unbiased estimators of the two elements, the variance of the microstructure noise and the fourth moment of the realized log returns, are also proposed to facilitate the estimation of integrated volatility. The asymptotic prop- erties and e®ectiveness of the proposed estimators are investigated both theoretically and via simulation study.