fit4=armaFit(~arima(4,0,0),fixed=c(NA,0,0,NA),include.mean=F,data=dw,method=\summary(fit4)
#例 5.9
ue=ts(scan(\读取数据 par(mfrow=c(2,2)) #绘制时序图 ts.plot(ue) #差分
due=diff(ue)
ddue=diff(due,lag=4) ts.plot(ddue)
Box.test(ddue,lag=6)
#平稳性检验 acf(ddue,lag=30) pacf(ddue,lag=30)
arima(ddue,order=c(0,0,0),method=\arima(ddue,order=c(4,0,0),method=\
arma=arima(ddue,order=c(4,0,0),transform.pars=F,fixed=c(NA,0,0,NA),include.mean=F,method=\ML\
#参数估计与检验（加载fArma程序包）
fit2=armaFit(~arima(4,0,0),include.mean=F,data=ddue,method=\summary(fit2)
fit3=armaFit(~arima(4,0,0),data=ddue,transform.pars=F,fixed=c(NA,0,0,NA),include.mean=F,method=\summary(fit3)
#残差白噪声检验
Box.test(arma$resid,6,fitdf=2,type=\
#拟合
ft=ts(fitted(fit3),start=1963.25,f=4) dft=ts(rep(0,115),start=1963.25,f=4) for(i in 1:115){dft[i]=ft[i]+due[i]+ue[i+4]} ts.plot(ue);lines(dft,col=\
##################################### #例5.10 乘积季节模型
wue=ts(scan(\
arima(wue,order=c(1,1,1),seasonal=list(order=c(0,1,1),period=12),include.mean=F,method=\)
################################### #拟合Auto-Regressive模型 eg1=ts(scan(\ts.plot(eg1)
#因变量关于时间的回归模型
fit.gls=gls(eg1~-1+time(eg1),correlation=corARMA(p=1),method=\summary(fit.gls2) #the results
#延迟因变量回归模型 leg1=lag(eg1,-1) y=cbind(eg1,leg1)
fit=arima(y[,1],c(0,0,0),xreg=y[,2],include.mean=F)
第六讲 #回顾 #例5.1
sha=ts(scan(\ts.plot(sha) diff(sha)
par(mfrow=c(2,1)) ts.plot(diff(sha)) acf(diff(sha))
#例5.2
car=ts(read.csv(\car
par(mfrow=c(3,1)) ts.plot(car) ts.plot(diff(car))
ts.plot(diff(car,differences=2))
#例5.3
milk=ts(scan(\milk
par(mfrow=c(3,1)) ts.plot(milk) ts.plot(diff(milk))
dm1=diff(diff(milk),lag=12) ts.plot(dm1) acf(dm1)
#例5.5
x=ts(cumsum(rnorm(1000,0,100))) ts.plot(x)
########################### #拟合ARIMA模型 #上机指导5.8.1 a=ts(scan(\par(mfrow=c(2,2)) ts.plot(a) da=diff(a) ts.plot(da) acf(da,20)
pacf(da,20) Box.test(da,6)
fit1=arima(a,c(1,1,0),method=\
predict(fit1,5,newxreg=(length(a)+1):(length(a)+5))
fit2=armaFit(~arima(1,1,0),data=a,xreg=1:length(a),method=\summary(fit1)
summary(fit2)#截距项不显著，故舍去 fit3=arima(a,c(1,1,0),method=\ predict(fit3,5)
#############################
#例5.8
incom=ts(read.csv(\incom
ts.plot(incom)
dincom=diff(incom) ts.plot(dincom)
acf(dincom,lag=18) #自相关图
Box.test(dincom,type=\白噪声检验 pacf(dincom,lag=18)
fit=arima(incom,order=c(0,1,1),xreg=1:length(incom),method=\
#见http://www.stat.pitt.edu/stoffer/tsa2/Rissues.htm
AutocorTest(fit$resid) #加载FinTS包 fore=predict(fit,10,newxreg=(length(incom)+1):(length(incom)+10)) #疏系数模型 #例5.8
w=ts(read.csv(\w=w[,1]
par(mfrow=c(2,2)) ts.plot(w) ts.plot(diff(w)) acf(diff(w),lag=18) pacf(diff(w),lag=18) dw=diff(w)
fit3=arima(dw,order=c(4,0,0),fixed=c(NA,0,0,NA,0),method=\Box.test(fit3$resid,lag=6,type=\Box.test(fit3$resid,lag=12,type=\
fit4=armaFit(~arima(4,0,0),fixed=c(NA,0,0,NA),include.mean=F,data=dw,method=\#加载fArma包 ，检验参数 summary(fit4)
#例 5.9 #读取数据
ue=ts(scan(\#绘制时序图
par(mfrow=c(2,2)) ts.plot(ue) #差分
due=diff(ue)
ddue=diff(due,lag=4) ts.plot(ddue)
Box.test(ddue,lag=6) #平稳性检验 acf(ddue,lag=30) pacf(ddue,lag=30)
arima(ddue,order=c(0,0,0),method=\arima(ddue,order=c(4,0,0),method=\
arma=arima(ddue,order=c(4,0,0),transform.pars=F,fixed=c(NA,0,0,NA),include.mean=F,method=\ML\
#参数估计与检验（加载fArma程序包）
fit2=armaFit(~arima(4,0,0),include.mean=F,data=ddue,method=\summary(fit2)
fit3=armaFit(~arima(4,0,0),data=ddue,transform.pars=F,fixed=c(NA,0,0,NA),include.mean=F,method=\summary(fit3)
#残差白噪声检验
Box.test(arma$resid,6,fitdf=2,type=\
#拟合
ft=ts(fitted(fit3),start=1963.25,f=4) dft=ts(rep(0,115),start=1963.25,f=4) for(i in 1:115){dft[i]=ft[i]+due[i]+ue[i+4]} ts.plot(ue);lines(dft,col=\
##################################### #例5.10 乘积季节模型
wue=ts(scan(\
arima(wue,order=c(1,1,1),seasonal=list(order=c(0,1,1),period=12),include.mean=F,method=\)
################################### #拟合Auto-Regressive模型 eg1=ts(scan(\ts.plot(eg1)
#因变量关于时间的回归模型
fit=arima(eg1,c(1,0,0),xreg=time(eg1),include.mean=F,method=\AutocorTest(fit$resid)#残差白噪声检验 ###另一种方法
fit.gls=gls(eg1~-1+time(eg1),correlation=corARMA(p=1),method=\summary(fit.gls2) #the results #延迟因变量回归模型 leg1=lag(eg1,-1)
y=cbind(eg1,leg1)
fit=arima(y[,1],c(0,0,0),xreg=y[,2],include.mean=F) AutocorTest(fit$resid)#残差白噪声检验
#p206 583拟合GARCH模型 library(tseries) library(fGarch) library(FinTS)
a=ts(scan(\ts.plot(a)
fit=lm(a~-1+time(a)) r=resid(fit) summary(fit) pacf(r^2) acf(r) acf(r^2)
AutocorTest(r) #残差是否存在序列相关 ArchTest(r) #是否存在ARCH效应
fit1=garchFit(~arma(2,0)+garch(1,1),data=r,algorithm=\summary(fit1)
#单位根检验
b=ts(read.csv(\ x=b[,1] y=b[,1]
summary(ur.df(x,type=\更多的单位根检验方法看帮助文档
#单位根检验更好的函数 加了画图的功能 library(fUnitRoots) urdfTest(x)
#协整检验
fit=arima(b[,2],xreg=b[,1],method=\r=resid(fit)
summary(ur.df(r,type=\Box.test(r,lag=6,fitdf=1)