[R-SIG-Finance] Problem with garch (tseries)
Ricardo Zambrano Aguilera
Ricardo.Zambrano at corpbanca.cl
Fri Aug 18 18:03:00 CEST 2006
greetings
i have a doubt with the meaning of the jarque bera test and ljung box test, all because of this...
1) why if i did simulate a garch(1,1) process with cond.dist="rnorm", then the jarque bera reject the null hyp??
2)what it say me the box-ljung test??
> creatingdata<-garchSim(model = list(omega = 1.0e-6, alpha = 0.1, beta = 0.8), n = 2000,
+ n.start = 100, presample = NULL, cond.dist = "rnorm", rseed = NULL)
> adjuste<-garch(creatingdata,order=c(1,1))
***** ESTIMATION WITH ANALYTICAL GRADIENT *****
> summary(adjuste)
Call:
garch(x = creatingdata, order = c(1, 1))
Model:
GARCH(1,1)
Residuals:
Min 1Q Median 3Q Max
-3.75511 -0.65994 0.01976 0.70273 3.12522
Coefficient(s):
Estimate Std. Error t value Pr(>|t|)
a0 8.245e-07 2.977e-07 2.770 0.00561 **
a1 8.083e-02 1.847e-02 4.376 1.21e-05 ***
b1 8.371e-01 4.198e-02 19.940 < 2e-16 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Diagnostic Tests:
Jarque Bera Test
data: Residuals
X-squared = 2.6605, df = 2, p-value = 0.2644
Box-Ljung test
data: Squared.Residuals
X-squared = 0.083, df = 1, p-value = 0.7732
>
> https://stat.ethz.ch/mailman/listinfo/r-sig-finance
More information about the R-SIG-Finance
mailing list