Coefficient and VCOV methods for Bayesian VARs
Retrieves coefficient / variance-covariance values from Bayesian VAR models
generated with bvar. Note that coefficients are available for
every stored draw and one may retrieve (a) credible intervals via the
conf_bands argument, or (2) means via the type argument.
## S3 method for class 'bvar'
coef(
object,
type = c("quantile", "mean"),
conf_bands = 0.5,
companion = FALSE,
...
)
## S3 method for class 'bvar'
vcov(object, type = c("quantile", "mean"), conf_bands = 0.5, ...)object |
A |
type |
Character scalar. Whether to return quantile or mean values. Note that conf_bands is ignored for mean values. |
conf_bands |
Numeric vector of confidence bands to apply.
E.g. for bands at 5%, 10%, 90% and 95% set this to |
companion |
Logical scalar. Whether to retrieve the companion matrix of
coefficients. See |
... |
Not used. |
Returns a numeric array of class bvar_coefs or
bvar_vcovs at the specified values.
# Access a subset of the fred_qd dataset
data <- fred_qd[, c("CPIAUCSL", "UNRATE", "FEDFUNDS")]
# Transform it to be stationary
data <- fred_transform(data, codes = c(5, 5, 1), lag = 4)
# Estimate a BVAR using one lag, default settings and very few draws
x <- bvar(data, lags = 1, n_draw = 1000L, n_burn = 200L, verbose = FALSE)
# Get coefficent values at the 10%, 50% and 90% quantiles
coef(x, conf_bands = 0.10)
# Only get the median of the variance-covariance matrix
vcov(x, conf_bands = 0.5)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.