# Predicting returns

In the previous exercises, we have assumed a constant mean by setting

garchspec <- ugarchspec(mean.model = list(armaOrder = c(0,0)),
variance.model = list(model = "gjrGARCH"),
distribution.model = "sstd")


In practice the predicted return $$\mu_t$$ is often time-varying. To capture this time-variation, one can use a GARCH-in-mean, AR(1), MA(1), ARMA(1,1) model, among others.

These models are implemented in rugarch and can be specified by changing the arguments for mean.model.

Which of the following statements is incorrect?