Realized Volatility in Noisy Prices: a MSRV approach

Volatility is the primary measure of risk in modern finance and volatility estimation and inference has attracted substantial attention in the recent financial econometric literature, especially in high-frequency analyses. High-frequency prices carry a significant amount of noise. Therefore, there are two volatility components embedded in the returns constructed using high frequency prices: the true volatility of the unobservable efficient returns and the volatility from the existence of microstructure noise. Researchers proposed several methodologies for estimating these two components but each of these estimators has its own pros and cons. however, some of them have higher rate of convergence. Multi-Scale Realized Volatility (MSRV) is one of these estimators that reported to have a high efficiency in estimating true realized volatility. In this paper, after estimating these two components through the MSRV approach, we investigate the relation between them. Our results suggest that there is a positive meaningful relation between microstructure noise and true realized volatility.