Correlation estimation using components of Japanese candlesticks

Abstract

Using the wick's difference from the classical Japanese candlestick representation of daily open, high, low, close prices brings efficiency when estimating the correlation in a bivariate Brownian motion. An interpretation of the correlation estimator in Rogers and Zhou (2008) in the light of wicks' difference allows us to suggest modifications, which lead to an increased efficiency and robustness against the baseline model. An empirical study on four major financial markets confirms the advantages of the modified estimator.