The effect of intraday periodicity on realized volatility measures

Abstract We focus on estimating daily integrated volatility ( IV ) by realized measures based intraday returns following a discrete-time stochastic model with pronounced periodicity (IP). demonstrate that neglecting the IP-impact estimators may lead to invalid statistical inference concerning for common finite number of returns. For given IP functional form, we analytically derive robust IP-correction factors as well their asymptotic distributions. show both in Monte Carlo simulations and empirically proposed bias corrections are way account computing estimators.