Set conjugate N-IW priors from lambdas as in Carriero
Carriero_priors(Y_in, Z_in = NULL, constant = TRUE, p = 4, lambdas = c(0.2, 1, 1, 1, 100, 100), delta = 1, s2_lag = NULL, y_0_bar_type = c("initial", "all"))
| Y_in | [T_in x m] multivariate time series |
|---|---|
| Z_in | [T_in x ...] exogeneous variables |
| constant | logical, default is TRUE, whether the constant should be included |
| p | number of lags |
| lambdas | vector = (l_1, l_lag, l_sc, l_io, l_const, l_exo), the l_kron is set to 1 automatically for conjugate N-IW prior. Short summary: sd(const in eq i) = l_const * sigma_i sd(exo in eq i)= l_exo * sigma_i sd(coef for var j lag l in eq i) = l_1*sigma_i/sigma_j/l^l_lag lambdas may be Inf l_io or l_sc equal to NA means no corresponding dummy observations |
| delta | vector [m x 1] or scalar or 'AR1'. Are used for prior Phi_1 and in sc/io dummy observations Scalar value is replicated m times. If set to 'AR1' then deltas will be estimated as AR(1) coefficients (but not greater than one). Diagonal of Phi_1 is equal to delta. y_0_bar is multiplied by delta componentwise. |
| s2_lag | number of lags in AR() model used to estimate s2 (equal to p by default) Carriero uses 1 in his matlab code |
| y_0_bar_type | (either 'all' or 'initial'). Determines how y_bar0 for sc and io dummy is calculated. 'all': y_bar0 is mean of y for all observations, 'initial': p initial observations Carriero: all, Sim-Zha: initial |
priors list containing Phi_prior [k x m], Omega_prior [k x k], S_prior [m x m], v_prior [1x1], where k = mp+d
Set conjugate N-IW priors from lambdas as in Carriero Based on Carriero "Bayesian VARs: Specification Choices and Forecast Accuracy" section 3.2
data(Yraw) priors <- Carriero_priors(Yraw, p = 4, lambdas = c(0.2, 1, 1, 1, 100, 100)) model <- bvar_conjugate0(priors = priors, keep = 100) # if something goes wrong then we need info! model <- bvar_conjugate0(priors = priors, keep = 10, verbose = TRUE)#>#>#>#>#>#>#>#>#>#>#>#>#>#>#>#>