tulpa_theta_matrix: A fit's outer grid as a named matrix

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

A fit's outer grid as a named matrix

Description

Coerces a nested-Laplace fit's theta_grid to matrix form with named axis columns. A single-axis grid is stored on the fit as a bare vector named by theta_names; every downstream reader that keys an axis by name needs the named matrix form, so this is the one place that coercion happens. Intended for reconstructing a fit's outer-grid posterior cell weights (see tulpa_grid_log_quad(), tulpa_normalise_weights_safe()) for a fit or path whose driver doesn't already carry fit$log_quad.

Usage

tulpa_theta_matrix(res)

Arguments

res	A tulpa_fit object (or any list carrying theta_grid and theta_names).

Value

res$theta_grid as an ⁠[n_cells x n_axes]⁠ matrix with axis names as column names, or NULL if the fit has no grid.

See Also

tulpa_grid_log_quad(), tulpa_normalise_weights_safe()

Examples

set.seed(1)
S <- 30L                                   # spatial units in a chain
nb <- lapply(seq_len(S), function(s) setdiff(c(s - 1L, s + 1L), c(0L, S + 1L)))
nn <- lengths(nb)
field <- as.numeric(scale(cumsum(rnorm(S, 0, 0.4))))
idx <- rep(seq_len(S), each = 6L); n <- length(idx); x <- rnorm(n)
y <- rbinom(n, 1L, plogis(-0.2 + 0.6 * x + field[idx]))
prior <- list(type = "icar", n_spatial_units = S, spatial_idx = idx,
              adj_row_ptr = c(0L, cumsum(nn)), adj_col_idx = unlist(nb) - 1L,
              n_neighbors = nn, tau_grid = c(0.5, 1, 2, 4, 8))
fit <- tulpa_nested_laplace(y, rep(1L, n), cbind(1, x), prior = prior,
                            family = "binomial",
                            control = list(progress = FALSE))
tulpa_theta_matrix(fit)

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