Hello,

I am not an expert in fitting GARCH models, but the computation
of residuals looks strange to me:

require(fGarch)
x <- rnorm(200)
g <- garchFit(formula ~ garch(1,1), x, include.mean = FALSE, trace =  
FALSE)
abs( residuals(g) ) - abs(x)

In fact, in general it outputs data +- mu. On the other hand, the  
output of

residuals(g, standard = TRUE)

looks more familiar, as it resembles other residuals:

require(tseries)
residuals(garch(x,trace=FALSE))

Is this behavior normal? Maybe I missed something, so thank you in  
advance for any comment or explanation.


David Morton de Lachapelle
Swissquote-EPFL


	[[alternative HTML version deleted]]