Forecasting realized volatility of Chinese stock market: A simple but efficient truncated approach

Abstract

In this study, we propose a new family of the heterogeneous autoregressive realized volatility (HAR-RV) models by considering truncated methods for predicting the RV in China's stock market. By adopting three types of critical values to recognize extremely large values of RV, we show that the modified models are simple but efficient to consistently deliver stronger in-sample and out-of-sample forecasting performances than those of existing methods. Models that take truncated approaches into account can generate substantial economic gains in applications. We further provide evidence that the superiority of our proposed models is derived from the reduced variance of the measurement errors during days including truncated RVs. Additionally, the improved performances of the modified models still hold after considering the effects of jump components and leverage, as well as a wide range of extensions and robustness analyses. K E Y W O R D SChina's stock market, HAR-RV model, truncated method, volatility forecasting | INTRODUCTIONVolatility and accurate forecasts of volatility in the stock market are crucial for asset pricing and risk management. Given the helpful role of high-frequency data in forecasting volatility, realized volatility (RV) based on intraday data, as pioneered by Andersen and Bollerslev (1998), receives much attention with regard to modeling and predicting financial market volatility (see, e.g.,

Predicting stock realized variance based on an asymmetric robust regression approach

“…In addition, He et al (2021) accurately forecast stock return volatility based on a robust regression model by considering the impact of outliers. D. Wen et al (2022) propose a new family of the HAR-RV models by considering truncated methods for predicting the RV in China's stock market. New models partially address the impact of outliers on forecasting performance.…”

“…D. Wen et al. (2022) propose a new family of the HAR‐RV models by considering truncated methods for predicting the RV in China's stock market. New models partially address the impact of outliers on forecasting performance.…”

Forecasting stock market returns with a lottery index: Evidence from China

“…On the one hand, the Chinese stock market has become the second largest in the world after the United States, with more than 5,000 listed companies and a total market capitalization exceeding 76 trillion yuan. The Chinese financial market is receiving increasing attention from investors and researchers (see, e.g., Dai & Zhang, 2023; Dai & Zhu, 2023; Ma & Cao, 2023; Wen et al, 2022; Zhang, He, Liao, & Wang, 2023). On the other hand, many studies have found a strong preference among retail investors for lottery‐like stocks (see, e.g., Han & Kumar, 2013; Kumar, 2009), and retail investors constitute the largest investor group in the Chinese stock market.…”

Forecasting China's stock market volatility with shrinkage method: Can Adaptive Lasso select stronger predictors from numerous predictors?

“…Therefore, accurately predicting volatility is a challenging task. Whether investors, academic researchers, or policy makers are concerned about how to improve the prediction accuracy of asset volatility (see, e.g., Nonejad, 2017; Gong & Lin, 2018; Ma et al, 2018; Ma, Liao, et al, 2019; Ma, Lu, et al, 2019; Wei et al, 2019; Vo & Tran, 2020; Lei et al, 2021; Wilms et al, 2021; Zhao et al, 2021; Qiu et al, 2022; Wen et al, 2022).…”