HierarchicalBVAR.prior_replications#

HierarchicalBVAR.prior_replications(n_replications=200, *, seed=None)[source]#

Data sets the prior generates, shaped like the effective sample.

Each replication draws (B, Sigma) from the prior – dummy observations folded in, as they are part of it – and simulates the sample from the observed presample with Gaussian innovations. Read the replicated statistics for what the prior deems plausible on the scale of the data: a Minnesota prior loose enough to admit explosive systems shows it here, before any sample is fitted.

Parameters:

  • n_replications (int) – Replicated data sets.

  • seed (int | Generator | None) – Seed or generator.

Return type:

NDArray[double]

Returns:

An array of shape (n_replications, nobs, k) aligned with observed.

Raises:

SpecificationError – If the count is not positive or the prior is unusable.