> da=read.table("d-usuk0107.txt")
> dim(da)
[1] 1588    4
> y=log(da[,4])
> x=diff(y)
> summaryStats(x)

Sample Quantiles:
      min        1Q    median       3Q     max
 -0.02171 -0.002747 0.0002805 0.003338 0.02093

Sample Moments:
      mean      std skewness kurtosis
 0.0001792 0.005139  -0.1425    3.602

Number of Observations:  1587

> autocorTest(x,lag=10)

Test for Autocorrelation: Ljung-Box

Null Hypothesis: no autocorrelation

Test Statistics:

Test Stat 10.1844
  p.value  0.4245

Dist. under Null: chi-square with 10 degrees of freedom
   Total Observ.: 1587

> archTest(x,lag=10)

Test for ARCH Effects: LM Test

Null Hypothesis: no ARCH effects

Test Statistics:

Test Stat 44.1489
  p.value  0.0000

Dist. under Null: chi-square with 10 degrees of freedom
   Total Observ.: 1587

> x=x*100
> m1=garch(x~1,~garch(1,1))
> summary(m1)

garch(formula.mean = x ~ 1, formula.var =  ~ garch(1, 1))

Mean Equation: x ~ 1

Conditional Variance Equation:  ~ garch(1, 1)

Conditional Distribution:  gaussian
--------------------------------------------------------------
Estimated Coefficients:
--------------------------------------------------------------
           Value Std.Error t value  Pr(>|t|)
       C 0.02344  0.012268   1.911 0.0562277
       A 0.00471  0.002106   2.236 0.0254756
 ARCH(1) 0.03577  0.009305   3.844 0.0001259
GARCH(1) 0.94583  0.015492  61.054 0.0000000
--------------------------------------------------------------
AIC(4) = 2344.029, BIC(4) = 2365.507

Normality Test:
--------------------------------------------------------------
 Jarque-Bera   P-value Shapiro-Wilk  P-value
       15.41 0.0004507       0.9966 0.001301

Ljung-Box test for standardized residuals:
--------------------------------------------------------------
 Statistic P-value Chi^2-d.f.
     9.384  0.6699         12

Ljung-Box test for squared standardized residuals:
--------------------------------------------------------------
 Statistic P-value Chi^2-d.f.
      9.57  0.6536         12

Lagrange multiplier test:
--------------------------------------------------------------
  Lag 1  Lag 2   Lag 3 Lag 4   Lag 5 Lag 6   Lag 7   Lag 8   Lag 9 Lag 10
 0.1566 -1.676 -0.9674 1.211 -0.0534 0.719 0.08344 -0.8265 -0.1659  1.273

 Lag 11   Lag 12       C
 0.7318 -0.05439 -0.3124

 TR^2 P-value F-stat P-value
 9.04  0.6995 0.8265  0.7252

> m2=garch(x~1,~garch(1,1),cond.dist="t")
> summary(m2)

garch(formula.mean = x ~ 1, formula.var =  ~ garch(1, 1), cond.dist = "t")

Mean Equation: x ~ 1

Conditional Variance Equation:  ~ garch(1, 1)

Conditional Distribution:  t
 with estimated parameter 13.74716 and standard error 4.978744
--------------------------------------------------------------
Estimated Coefficients:
--------------------------------------------------------------
           Value Std.Error t value  Pr(>|t|)
       C 0.02482  0.012171   2.040 0.0415647
       A 0.00364  0.002146   1.696 0.0900312
 ARCH(1) 0.03627  0.010310   3.518 0.0004479
GARCH(1) 0.94980  0.016015  59.305 0.0000000
--------------------------------------------------------------
AIC(5) = 2333.037, BIC(5) = 2359.885

Normality Test:
--------------------------------------------------------------
 Jarque-Bera   P-value Shapiro-Wilk  P-value
       16.49 0.0002632       0.9965 0.001091

Ljung-Box test for standardized residuals:
--------------------------------------------------------------
 Statistic P-value Chi^2-d.f.
     9.383  0.6699         12

Ljung-Box test for squared standardized residuals:
--------------------------------------------------------------
 Statistic P-value Chi^2-d.f.
     9.353  0.6725         12

Lagrange multiplier test:
--------------------------------------------------------------
  Lag 1  Lag 2   Lag 3 Lag 4   Lag 5 Lag 6   Lag 7   Lag 8   Lag 9 Lag 10
 0.1138 -1.688 -0.8668 1.187 -0.1045 0.754 0.04652 -0.8261 -0.2602   1.26

 Lag 11   Lag 12       C
 0.7055 -0.05438 -0.2461

 TR^2 P-value F-stat P-value
 8.82  0.7182 0.8064  0.7453

> predict.garch(m2,5)
$series.pred:
[1] 0.02482319 0.02482319 0.02482319 0.02482319 0.02482319

$sigma.pred:
[1] 0.4007978 0.4025418 0.4042542 0.4059356 0.4075868

$asymp.sd:
[1] 0.5110539