Re: [R] garch in tseries

From: Spencer Graves <>
Date: Thu 04 May 2006 - 02:46:41 EST

Dear Erin:

          I just realized I had misread your question. Have you tried sending your question directly to the 'tseries' maintainer, listed with help(package="tseries")?

          While I misread your question earlier, it looks to me like you could get what you want by first subtracting some number close to the mean or median, then using garchFit{fSeries}. If you can't get that to work, could you please notify both Diethelm Wuertz and me?

	  Best Wishes,
	  spencer graves
	  The documentation for my currently installed version of
garchFit{fSeries} indicates that the default include.mean = TRUE.

          How do you know "it didn't work"? With the default include.mean = TRUE, the following took just under a minute on my IBM T-30 notebook:

# Load Time Series:
# Vector of Compounded Returns:
x <- diff(sp500dge[,1])
# Vector of Percentage Compounded Returns: X = 100*x
fit = garchFit(~arma(0,1), ~garch(1,1), series = X)

          Moreover, print(fit) included a parameter 'mu' whose names suggests that it is a mean that might not bre estimated if 'include.mean = FALSE'.

          However, when I tried it, it went into an apparent infinite loop, which I killed after ~15-20 minutes:

fit0 = garchFit(~arma(0,1), ~garch(1,1), series = X,


          I got a similar potentially infinite loop from the following:

fit2 = garchFit(~arma(0,1), ~garch(1,1), series = X+100)

          However, the following converged and estimated mu at 0.1000, as simulated:

fit.1 = garchFit(~arma(0,1), ~garch(1,1), series = X+0.1)

          Conclusion: The code seems to work as documented, sometimes. Unfortunately, it appears to have a disturbing affinity for an apparent infinite loop, and I don't have the time now to diagnose it further.

	  hope this helps.
	  spencer graves

Erin Hodgess wrote:

> Hello again!
> Is there a way to include a mean in the garch function in the
> library(tseries), please?
> I tried include.mean=T in the function statement but it didn't work
> thanks in advance!
> R Version 2.2.1 Windows
> Sincerely,
> Erin
> mailto:
> ______________________________________________
> mailing list
> PLEASE do read the posting guide! mailing list PLEASE do read the posting guide! mailing list PLEASE do read the posting guide! Received on Thu May 04 02:56:30 2006

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.1.8, at Thu 04 May 2006 - 04:09:58 EST.

Mailing list information is available at Please read the posting guide before posting to the list.