tulpa_spde_log_hyperprior: SPDE field hyperprior log density on (range, sigma)

In tulpa: Templated Unified Library for Posterior Approximation in Bayesian Hierarchical Models

SPDE field hyperprior log density on (range, sigma)

Description

The SPDE field's hyperprior on ⁠(range, sigma)⁠, evaluated as a density on ⁠(log range, log sigma)⁠ – the coordinates every SPDE outer integrator works in (grid, CCD and k-hat alike, gcol33/tulpa#731). Intended for a caller running its own outer-grid loop over ⁠(range, sigma)⁠ around a coupled model tulpa's own SPDE front doors do not fit directly.

Usage

tulpa_spde_log_hyperprior(range, sigma, sp, hyperprior = "proper")

Arguments

range, sigma	Numeric vectors of range / marginal-SD nodes (natural scale, recycled against each other).
sp	A spatial_spde() / spatial_spde_custom() spec, carrying the declared or defaulted prior_range / prior_sigma anchors.
hyperprior	"proper" (default) or "flat"; see ?spatial_spde.

Value

Numeric vector of log-density values, one per ⁠(range, sigma)⁠ pair.

See Also

tulpa_spde_precision_Q(), spatial_spde()

Examples

n <- 6L
G <- Matrix::bandSparse(n, k = c(-1, 0, 1),
                        diagonals = list(rep(-1, n - 1), c(1, rep(2, n - 2), 1),
                                         rep(-1, n - 1)))
sp <- spatial_spde_custom(Matrix::Diagonal(n), G, Matrix::Diagonal(n),
                          prior_range = c(1, 0.5), prior_sigma = c(1, 0.01))
tulpa_spde_log_hyperprior(range = c(0.5, 1, 2), sigma = 1, sp = sp)

tulpa documentation built on Oct. 19, 2026, 5:09 p.m.