论文部分内容阅读
构建多元线性和半参数单指数自回归条件持续时间标值模型及其估计方法,基于分笔交易数据研究中国股票市场交易与信息之间的线性与非线性动态关系。实证结果表明:(1)交易持续时间存在明显正自相关性、过度分散性和聚集效应;(2)滞后收益率、成交量、买卖价差对交易持续时间有显著线性正影响,滞后波动率对交易持续时间有显著线性负影响,各滞后市场微观结构特征变量对交易持续时间的影响普遍支持Easley和O’Hara(1992)“无交易预示着无消息”的发现;(3)滞后收益率、波动率、成交量和买卖价差对交易持续时间的非线性正、负影响有差异,各滞后市场微观结构特征变量对交易持续时间的影响没有一致性的结论,Diamond和Verrechia(1987)的“无交易预示着坏消息”以及Easley和O’Hara(1992)的“无交易预示着无消息”的结论同时成立。
Constructing the multivariate linear and semi-parametric exponential autoregressive conditional duration model and its estimation method, the paper studies the linear and nonlinear dynamic relationship between transaction and information in Chinese stock market based on transaction data. The empirical results show that: (1) there is a significant positive correlation, over-dispersion and aggregation effect on the duration of the transaction; (2) lagged return, trading volume and bid-ask spread have a significant linear positive impact on the duration of the transaction, Transaction duration has a significant linear negative impact, and lagging market micro-structure characteristic variables on the duration of the transaction generally support Easley and O’Hara (1992) “No transaction indicates no news ” findings; (3) Lag recovery Rate and volatility, trading volume and bid-ask spread have different positive and negative nonlinear effects on the duration of the transaction, and there is no consistency between the lagged market microstructure variables and transaction duration. Diamond and Verrechia (1987) “No trades foreshadow bad news” and the conclusion “Easley and O’Hara (1992) ’s” No trades indicate no message "came true at the same time.