IndependentNormalWishartPrior.sum_of_coefficients

IndependentNormalWishartPrior.sum_of_coefficients: float | None

Confidence in the sum-of-coefficients restriction \(\lambda_5\), or None.

When given, dummy_observations() contributes one row per variable, exactly as MinnesotaPrior does. Under the Gibbs model dummy rows are stacked under the sample before every sweep. Must be positive when given.