> setwd("C:/teaching/ama")
> library(tseries)
Loading required package: quadprog
'tseries' version: 0.9-27
'tseries' is a package for time series analysis and computational
finance.
> da=read.table("T7-4.DAT") % Load data
> dim(da)
[1] 63 5
> da[1,]
V1 V2 V3 V4 V5
1 227 32 30 12 1
> y=da[,1]
> x=da[,2:5]
> x1=as.matrix(x)
> m1=lm(y~x1) % Fit a multiple linear regression (linear model).
> summary(m1)
lm(formula = y ~ x1)
Residuals:
Min 1Q Median 3Q Max
-36.521 -13.817 -2.781 13.556 35.832
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.8581 11.5561 0.161 0.87282
x1V2 5.8742 0.2905 20.219 < 2e-16 ***
x1V3 1.4052 0.2928 4.799 1.16e-05 ***
x1V4 1.3154 0.5787 2.273 0.02675 *
x1V5 -15.8571 5.3344 -2.973 0.00429 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 18.32 on 58 degrees of freedom
Multiple R-Squared: 0.9521, Adjusted R-squared: 0.9488
F-statistic: 288.1 on 4 and 58 DF, p-value: < 2.2e-16
> names(m1)
[1] "coefficients" "residuals" "effects" "rank"
[5] "fitted.values" "assign" "qr" "df.residual"
[9] "xlevels" "call" "terms" "model"
> Box.test(m1$residuals,lag=10,type='Ljung')
Box-Ljung test
data: m1$residuals
X-squared = 48.1743, df = 10, p-value = 5.768e-07
> acf(m1$residuals)
> pacf(m1$residuals)
> m2=arima(y,xreg=x1,order=c(1,0,0),seasonal=list(order=c(1,0,0),period=7))
> m2
Call:
arima(x = y, order = c(1, 0, 0), seasonal = list(order = c(1, 0, 0), period = 7),
xreg = x1)
Coefficients:
ar1 sar1 intercept V2 V3 V4 V5
0.5414 0.3753 7.7211 5.7066 1.4087 1.2008 -10.0592
s.e. 0.1067 0.1157 12.5670 0.2195 0.2211 0.3840 6.0951
sigma^2 estimated as 188.2: log likelihood = -255.09, aic = 526.18
> Box.test(m2$residuals,lag=10,type='Ljung')
Box-Ljung test
data: m2$residuals
X-squared = 7.0855, df = 10, p-value = 0.7173
> acf(m2$residuals)
> tsdiag(m2)