r语言arch模型分析报告 附数据代码.docx

R代码复制到相应后面(能附上运行得到的图不)
数据读取和处理(为减少误差,估计时根据每个交易日的收盘价对日收益率进行自然
对数处理,即收益率r=log(/).
#读取数据
golddata= ("")
#
# $minimum
# [1] -
#直方图
hist (Valuedata1)
Histogram of Valuedatal
A 口匚QJnbalLL
Valuedata 1
通过R软件得到 指数日收益率直方图
,其分布是右偏的, ,远高于正态分布 ,收益率不服从正态分布,即利用所用基于正态分布统计方法对收益 率序的检验均失效
收益率序列的平稳性检验〔ADF检验〕
library (tseries)
平稳性检验最常用的方法为单位根方法,运用 R软件,对日收益率进行单位根检验,检 验结果如下
print ( (diff (Valuedatal), alternative = "stationary" , k=0))
# Warning in (diff(Valuedata1), alternative = "stationary", k
=0):
# p-value smaller than printed p-value
#
# Augmented Dickey-Fuller Test
#
# data: diff(Valuedata1)
# Dickey-Fuller = -, Lag order = 0, p-value =
# alternative hypothesis: stationary
从单位根检验结果可看出： 单位根检验的p-value ,从而拒绝
原假设,说明收益率不存在单位根,是平稳序列,即服从I(0)过程
#通过R软件画出日收益率的自相关图和收益率的偏自相关图 acf (Valuedatal)
Series Valuedatal
o
Q
9
O
LL
O





pacf (Valuedatal)
Series Valuedatal
#从自相关图和偏自相关图的结果来看,对数收益率的自相关函数值和偏自相关函数值很 快落入置信区间,因此对数收益率稳定.
ARCH效应检验
library (FinTS)
# Loading required package: zoo
#
# Attaching package: 'zoo'
# The following objects are masked from 'package:base':
#
# ,
getSymbols("XPT/USD",src="oanda")
Valuedata1
ones<- rep ( 1, length (Valuedata1))
ols<- lm(Valuedata1〜ones);01s
#
# Call:
# lm(formula = Valuedatal ~ ones)
#
# Coefficients:
# (Intercept) ones
# - NA
residuals<-ols$residuals
ArchTest (residuals, lags= 1)
#
# ARCH LM-test; Null hypothesis: no ARCH effects
#
# data: residuals
# Chi-squared = , df = 1, p-value = -16
ArchTest (residuals, lags= 5)
#
# ARCH LM-test; Null hypothesis: no ARCH effects
#
# data: residuals
# Chi-squared = , df = 5, p-value < -16
ArchTest (residuals, lags= 12)
#
# ARCH LM-test; Null hypothesis: no ARCH effects
#
# data: residuals
# Chi-squared = , df = 12, p-v