Dear R users,
I need to estimate an ARCH(1,0) model with t-residuals. To do this I use
garchFit
function from fGarch library. However, I get the following error message:
Error in.garchInitParameters (formula.mean = formula.mean, formula.var =
formula.var, ): object "alpha" not found
I tried to estimate this model with different series, but I always get this
error message.
For example,
data(EuStockMarkets)
dax <- diff(log(EuStockMarkets))[,"DAX"]
g=garchFit(formula=~garch(0,1),data=dax,cond.dist="dstd",include.mean=FALSE)
Series Initialization:
ARMA model: arma
Formula mean: ~ arma(0, 0)
GARCH model: garch
Formula var: ~ garch(0, 1)
ARMA Order: 0 0
Max ARMA Order: 0
GARCH Order: 0 1
Max GARCH Order: 1
Maximum Order: 1
h.start: 2
llh.start: 1
Length of Series: 1859
Recursion Init: mci
Series Scale: 0.01030084
Error in .garchInitParameters(formula.mean = formula.mean, formula.var =
formula.var, :
object "alpha" not found
If I use GARCH(0,1) model I get the following error message:
g=garchFit(formula=~garch(0,1),data=dax,cond.dist="dstd",include.mean=FALSE)
Series Initialization:
ARMA model: arma
Formula mean: ~ arma(0, 0)
GARCH model: garch
Formula var: ~ garch(1, 0)
ARMA Order: 0 0
Max ARMA Order: 0
GARCH Order: 1 0
Max GARCH Order: 1
Maximum Order: 1
h.start: 2
llh.start: 1
Length of Series: 1859
Recursion Init: mci
Series Scale: 0.01030084
Error in sum(beta) : invalid 'type' (closure) of argument
Do fGarch function allow to estimate GARCH(p,q) with p and q >0 only? Are there
any other functions in order to estimate ARCH(1,0) with
t-residuals?
Thank you.
Regards,
Elena
Advertisement:
Lietuviams reikia saugios pasto dezutes.
Dideles ir saugios.
INBOX.LT - 10 GB nemokamas pastas!
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
