FittedVAR

FittedVAR — reduced-form posterior from Bayesian VAR estimation.

FittedVAR

Bases: BaseModel

Immutable container for a fitted (reduced-form) Bayesian VAR.

Attributes:

Name	Type	Description
idata	InferenceData	ArviZ InferenceData with posterior draws.
n_lags	int	Lag order used in estimation.
data	VARData	Original VARData used for fitting.
var_names	list[str]	Names of endogenous variables.

coefficients property

Posterior draws of B coefficient matrices.

has_exog property

Whether the model includes exogenous variables.

intercepts property

Posterior draws of intercept vectors.

sigma property

Posterior draws of residual covariance matrix.

forecast(steps, exog_future=None)

Produce h-step-ahead forecasts from the reduced-form posterior.

Parameters:

Name	Type	Description	Default
steps	int	Number of forecast steps.	required
exog_future	ndarray | None	Future exogenous values, shape (steps, k). Required if model has exog.	None

Returns:

Type	Description
ForecastResult	ForecastResult with posterior forecast draws.

set_identification_strategy(scheme)

Apply a structural identification scheme.

Parameters:

Name	Type	Description	Default
scheme	IdentificationScheme	An IdentificationScheme protocol instance (e.g. Cholesky).	required

Returns:

Type	Description
IdentifiedVAR	IdentifiedVAR with structural shock matrix in the posterior.