基于GARCH模型的高频金融数据的量价分析  

Quantitative and price analysis of high-frequency financial data based on GARCH models

作　　者：杨凯 于鑫洋 蓬勃 韩雪 陈铭 YANG Kai;YU Xin-yang;PENG Bo;HAN Xue;CHEN Ming(School of Mathematics and Statistics,Changchun University of Technology,Changchun 130012,China)

机构地区：[1]长春工业大学数学与统计学院,吉林长春130012

出　　处：《吉林师范大学学报（自然科学版）》2021年第4期26-30,共5页Journal of Jilin Normal University:Natural Science Edition

基　　金：国家自然科学基金项目(11901053);全国大学生创新创业项目(2021cxcy139)。

摘　　要：采用GARCH模型及其衍生模型对万科A(000002)高频交易数据进行拟合与分析,对比了6种不同GARCH模型的拟合结果,结果显示:带有成交量的3个模型的拟合精度一致优于不带成交量的同类模型,这说明了成交量对股票价格和收益率有显著影响.进一步对收益率与成交量进行格兰杰因果检验,结果表明,股票价格变化与成交量之间存在一定的因果关系.The GARCH model and its derivative model were used to fit and analyze the high-frequency trading data of Vanke A(000002),and the fitting results of six different GARCH models were compared.The fitting results showed the fitting accuracy of the three models with volume is consistently superior to that of the same model without volume,which showed that the volume has a significant impact on stock prices and yields.Further,Granger causality test was conducted on the rate of return and volume.The results showed that there was a certain causal relationship between stock price changes and volume.

关 键 词：高频数据 GARCH-M模型 因果检验 量价关系 

分 类 号：O212[理学—概率论与数理统计]