MEM_MIDAS_lr_pred: MEM-MIDAS long-run one-step-ahead predictions (with skewness...

In rumidas: Univariate GARCH-MIDAS, Double-Asymmetric GARCH-MIDAS and MEM-MIDAS

MEM-MIDAS long-run one-step-ahead predictions (with skewness parameter)

Description

Predicts the long-run term of the dependent variable, usually the realized volatility, for the MEM-MIDAS, with an asymmetric term linked to past negative returns.

Usage

MEM_MIDAS_lr_pred(param, x, daily_ret, mv_m, K)

Arguments

param	Vector of estimated values. It must be a six–dimensional vector. See the example below.
x	Dependent variable, usually the realized volatility. It must be positive and "xts" object.
daily_ret	Daily returns, which must be an "xts" object.
mv_m	MIDAS variable already transformed into a matrix, through mv_into_mat function.
K	Number of (lagged) realizations of the MIDAS variable to consider.

Value

The resulting vector is the log-likelihood value for each i,t.

References

\insertAllCited

See Also

mv_into_mat.

Examples

est_val<-c(alpha=0.10,beta=0.8,gamma=0.1,m=0,theta=-0.16,w2=5)
r_t<-sp500['/2010']
real<-(rv5['/2010'])^0.5		# realized volatility
mv_m<-mv_into_mat(real,diff(indpro),K=12,"monthly")
est_vol<-MEM_MIDAS_pred(est_val,real,r_t,mv_m,K=12)
head(est_vol)

rumidas documentation built on April 4, 2025, 1:01 a.m.