HorseshoePrior.deterministic_scale

HorseshoePrior.deterministic_scale: float

Prior standard deviation of the unshrunk rows, in residual-scale units.

The intercept, any trend, and any exogenous regressor of equation \(i\) get variance \((\text{deterministic\_scale} \cdot s_i)^2\), held fixed across sweeps. Ten is loose enough to be uninformative for standardized data and finite enough to keep the prior proper. Must be positive.