Statistics and Its Interface

Volume 11 (2018)

Number 1

On the surprising explanatory power of higher realized moments in practice

Pages: 153 – 168

DOI: http://dx.doi.org/10.4310/SII.2018.v11.n1.a13

Authors

Keren Shen (Department of Statistics and Actuarial Science, University of Hong Kong, Pokfulam, Hong Kong)

Jianfeng Yao (Department of Statistics and Actuarial Science, University of Hong Kong, Pokfulam, Hong Kong)

Wai Keung Li (Department of Statistics and Actuarial Science, University of Hong Kong, Pokfulam, Hong Kong)

Abstract

Realized moments of higher order computed from intraday returns have been introduced in recent years. The literature indicates that realized skewness is an important factor in explaining future asset returns. However, the literature mainly focuses on the whole market, as well as the monthly or weekly scale. In this paper, we conduct an extensive empirical analysis to investigate the forecasting abilities of realized skewness and realized kurtosis towards an individual stock’s future return and variance in the daily scale. It is found that realized kurtosis possesses significant forecasting power for the stock’s future variance and in contrast with the existing literature, realized skewness is lack of explanatory power of future daily returns for individual stocks in the short term.

Keywords

high-frequency, realized variance, realized kurtosis, linear regression, trading volume

2010 Mathematics Subject Classification

Primary 62P20. Secondary 91B84.

Full Text (PDF format)

The second author’s research is partially supported by HK GRF Grant (17332416). The third author’s research is partially supported by HK GRF Grant (17303315).

Received 18 April 2017

Published 23 August 2017