ScaleIG.setup_gibbs_inference()#

ScaleIG.setup_gibbs_inference(coef, penalty=None)[source]#

Sets up a liesel.goose.GibbsKernel for this variable, assuming that it is used as the variance parameter in a structured additive term.

See the docs for the class ScaleIG for a description of the Gibbs sampler.

Note

Usually, this method does not have to be called manually, when you are working with StrctTernm objects or initializing terms using TermBuilder.

Parameters:

coef (Var) – Coefficient variable.
penalty (Array | ndarray | bool | number | bool | int | float | complex | None, default: None) – Penalty matrix. If None, the penalty is assumed to be the identity matrix of a dimension fitting the coefficient dimension.

ScaleIG.setup_gibbs_inference()