Key points are not available for this paper at this time.
This paper examines the incorporation of higher moments in portfolio selection problems utilising high-frequency data. Our approach combines innovations from the realised volatility literature with a portfolio selection methodology utilising higher moments. We provide an empirical study of the measurement of higher moments from tick by tick data and implement the model for a selection of stocks from the DOW 30 over the time period 2005–2011. We demonstrate a novel estimator for moments and co-moments in the presence of microstructure noise.
Buckle et al. (Wed,) studied this question.