Obtains the log-likelihood of the GARCH-MIDAS with two low-frequency variables, with an asymmetric term linked to past negative returns, according to two errors' conditional distributions: Normal and Student-t. For details, see engle_ghysels_sohn_2013;textualrumidas and conrad_lock_2015;textualrumidas.
GM_2M_loglik(
param,
daily_ret,
mv_m_1,
mv_m_2,
K_1,
K_2,
distribution,
lag_fun = "Beta"
)
The resulting vector is the log-likelihood value for each
Vector of starting values.
Daily returns, which must be an "xts" object.
first MIDAS variable already transformed into a matrix, through mv_into_mat
function.
second MIDAS variable already transformed into a matrix, through mv_into_mat
function.
Number of (lagged) realizations of the first MIDAS variable to consider.
Number of (lagged) realizations of the second MIDAS variable to consider.
The conditional density to use for the innovations. At the moment, valid choices are "norm" and "std", for the Normal and Student-t distributions.
optional. Lag function to use. Valid choices are "Beta" (by default) and "Almon", for the Beta and Exponential Almon lag functions, respectively.
mv_into_mat
.
# \donttest{
# conditional density of the innovations: normal
start_val<-c(alpha=0.01,beta=0.8,gamma=0.05,m=0,theta_1=0.1,w2_1=2,theta_2=0.1,w2_2=2)
r_t<-sp500['2005/2010']
mv_m_1<-mv_into_mat(r_t,diff(indpro),K=12,"monthly")
mv_m_2<-mv_into_mat(r_t,diff(indpro),K=24,"monthly")
sum(GM_2M_loglik(start_val,r_t,mv_m_1,mv_m_2,K_1=12,K_2=24,distribution="norm"))
# }
Run the code above in your browser using DataLab