PTMCoef.new_rw1_fromzero_ig()

PTMCoef.new_rw1_fromzero_ig()#

classmethod PTMCoef.new_rw1_fromzero_ig(knots, ig_concentration, ig_scale, inference=None, name='', scale_penalty=True, diagonalize_penalty=True, role='transformation_coef')[source]#

Create from-zero RW1 coefficients with an inverse-gamma prior on the variance parameter.

Parameters:

  • knots (Any) – Knot vector for the spline basis.

  • ig_concentration (float) – Concentration parameter for the inverse-gamma prior on scale.

  • ig_scale (float) – Scale parameter for the inverse-gamma prior on scale.

  • inference (Any) – Optional inference specification for the latent parameter, a liesel.goose.MCMCSpec object. By default, uses a Gibbs sampler. (default: None)

  • name (str) – Optional base name for created variables. (default: '')

  • scale_penalty (bool) – Whether to scale the penalty matrix to unit infinity norm. (default: True)

  • diagonalize_penalty (bool) – Whether to diagonalize the penalty via a eigenvalue decomposition. (default: True)

  • role (str) – Role assigned to the latent coefficient variable. (default: 'transformation_coef')

Return type:

Self

Returns:

PTMCoef – Configured coefficient with inverse-gamma prior on the variance parameter.

Contents