基于极端分位回归的股市收益与交易量相依性研究

The Dependence of Return-volume in Chinese Industry Stock Markets:Empirical Evidence from Quantile Regression

依据中国行业股市收益和交易量时间序列数据,引入政策效应变量,运用分位数回归理论时间序列模型,考量股市收益与交易量相依性关系。结果显示,中国行业股市收益与交易量之间相关关系存在差异,且在高分位点呈现正相关,在低分位点呈现负相关。结果表明,中国股市投资者存在显著的羊群效应,政策效应对不同行业收益和交易量相依性的影响存在异质性。鉴此,投资者宜减少部分行业股票配置,政府应建立高效的风险管理机制,尽量减缓股市波动。

This,paper adopts Quantile regression to analyze the dependence between trading volume and industry stock returns in the Chinese industry stock markets in the period from January 1996 to June 2016. We also investigate the effects of exogenous government policies on the relation between trading volume and stock return. OLS results indicate no significant dependence between volume and returns. However, our empirical results of the Quantile regression method reveals the magnitude of nonlinear effects is heterogeneous across industries. Specifically, its positive for high return quantiles and negative for low ones. In an economic viewpoint, this paper contributes to a better understanding of activity of different industries market participants during extreme events and government policies.