基于ARMA-GARCH模型的股票价格分析与预测  

Analysis and Prediction of Stock Price Based on ARMA-GARCH Model

作　　者：杨琦[1] 曹显兵[1] 

机构地区：[1]北京工商大学理学院,北京100048

出　　处：《数学的实践与认识》2016年第6期80-86,共7页Mathematics in Practice and Theory

基　　金：北京市高校创新人才项目(201306026)

摘　　要：利用时间序列模型对大众公用(600635)股票价格进行分析与预测.首先,通过对数据的初步分析,建立ARMA拟合模型;然后,通过模型检验发现模型残差中存在条件异方差性,通过加入GARCH项消除条件异方差性,得到了ARMAGARCH拟合模型;最后实证分析结果表明了模型的有效性与准确性.This paper uses some models in time series to predict the price of stock DaZhong- GongYong（600635）. Firstly, an ARMA model is built based on the preliminary analysis of data. Secondly, the conditional heteroscedasticity in the residual error of the model is found after model testing, and a more reasonable ARMA-GARCH model which can eliminate the conditional heteroscedasticity is set up for the stock. Finally, the empirical analysis shows that the model is effective and accurate.

关 键 词：时间序列 ARMA模型 ARMA-GARCH模型 股票预测 R软件 

分 类 号：F832.51[经济管理—金融学] F224