Man pages for tulpa
Templated Unified Library for Posterior Approximation in Bayesian Hierarchical Models
| adjacency | Construct a spatial adjacency graph for areal models |
| agq_fit | Adaptive Gauss-Hermite quadrature for one-RE GLMMs |
| AIC.tulpa_fit | Information criteria on a tulpa fit |
| as_draws | Posterior draws in the posterior package's format |
| auto_grid | Mark an outer-grid setting as a default rather than a pin |
| auto_grid_place | May the placement pass move a marked outer-grid axis? |
| bayes_R2 | Bayesian R-squared |
| bridge_sampling | Bridge sampling for marginal likelihood |
| categorical_accessors | Observation-level accessors for categorical fits |
| ccd_grid | Central composite design (CCD) grid for nested-Laplace... |
| ccd_to_theta | Map standardised CCD coordinates to physical hyperparameters |
| ccd_weights | Corrected R-INLA CCD integration weights |
| check_adjacency | Validate a spatial adjacency matrix |
| check_diagnostics | Quick convergence check |
| check_model | Diagnostic panel plot |
| coef.tulpa_fit | Fixed-effect coefficients |
| compare_models | Compare models by information criteria |
| compute_nngp_neighbors | Compute nearest neighbors for NNGP |
| confint.tulpa_fit | Credible intervals for the fixed effects |
| criteria_doors | DIC, CPO, WAIC and PSIS-LOO on a fit |
| diagnostics | Posterior diagnostics for a fitted model |
| diagnostic_summary | Comprehensive diagnostic summary |
| durbin_watson | Durbin-Watson test for temporal autocorrelation |
| energy_bfmi | Energy Bayesian Fraction of Missing Information (E-BFMI) |
| family_names | Supported R-level family names |
| field_effects | Spatial field effects per unit |
| findbars | Find all bar terms in a formula's parse tree |
| fit_spde | Fit a spatial model using SPDE Laplace approximation |
| fit_st_nested | Fit an additive spatiotemporal GLM by nested Laplace |
| fitted.tulpa_fit | Fitted values (population level) |
| fixef | Fixed-effect coefficients (lme4-compatible) |
| geweke_test | Geweke convergence test |
| glance.tulpa_fit | Model-level summary statistics (broom-compatible) |
| hyper_axis_spec | Describe one outer-grid hyperparameter axis |
| imh_laplace | Independence Metropolis-Hastings with Laplace proposal |
| inference_mode_info | Print inference mode information |
| is_auto_grid | Is an outer-grid setting marked as a default? |
| latent | Mark an expression as a latent block in a tulpa formula |
| latent_factor | Create a latent factor specification |
| latent_factors | Extract latent factor posteriors from fit |
| logLik.tulpa_fit | The fit's log-scale goodness quantity |
| mala | Metropolis-adjusted Langevin algorithm (MALA) |
| mcmc_draws | MCMC chain draws from a fit |
| model_average | Model-averaged predictions |
| moran_i | Moran's I test for spatial autocorrelation in residuals |
| n_divergent | Number of divergent transitions |
| nobars | Remove all bar terms from a formula's parse tree |
| nobs.tulpa_fit | Number of observations in a tulpa fit |
| node_index | Map cell identifiers to graph node indices |
| pathfinder | Pathfinder: variational warm-start via L-BFGS + ELBO scoring |
| pit_residuals | PIT (probability integral transform) residuals |
| plot_acf | Plot autocorrelation functions |
| plot_diagnostics | Diagnostic plotting functions for tulpa models |
| plot_divergences | Plot divergent transitions |
| plot_energy | Plot energy diagnostic (E-BFMI) |
| plot_ess | Plot effective sample size diagnostic |
| plot_map | Plot spatial predictions as a map |
| plot_map_panel | Plot multiple maps in a grid |
| plot_pairs | Plot bivariate parameter posteriors (pairs plot) |
| plot_rhat | Plot Rhat convergence diagnostic |
| plot.tulpa_fit | Plot fixed-effect posteriors |
| plot.tulpa_prior_predict | Plot method for tulpa_prior_predict |
| plot.tulpa_st_summary | Plot method for spatiotemporal effects |
| plot.tulpa_svc_posterior | Plot method for tulpa_svc_posterior |
| plot.tulpa_temporal_posterior | Plot method for tulpa_temporal_posterior |
| plot.tulpa_tvc_posterior | Plot method for tulpa_tvc_posterior |
| posterior_predict | Posterior predictive replicates |
| posterior_sample | Posterior parameter sample from a fit |
| post_hoc_lm | Fit a post-hoc linear model on estimated parameters |
| pp_check | Posterior predictive check |
| predict.tulpa_fit | Predict at new covariate values (population level) |
| prior_beta | Beta prior |
| prior_exponential | Exponential prior |
| prior_from_spec | Build a 'prior' list for 'tulpa_nested_laplace()' from a... |
| prior_gamma | Gamma prior |
| prior_half_cauchy | Half-Cauchy prior |
| prior_half_normal | Half-normal prior |
| prior_normal | Normal prior |
| prior_pc | Penalized complexity (PC) prior |
| prior_predict | Prior predictive simulation |
| priors_default | Show default priors for a tulpa family |
| ranef | Random-effect summaries |
| re_cov_pc_lkj_prior | PC + LKJ hyperprior for a random-effect covariance |
| reexports | Objects exported from other packages |
| residuals.tulpa_fit | Residuals from a tulpa fit |
| rubins_pool | Pool multiple imputation draws via Rubin's rules |
| sbc | Simulation-based calibration |
| sbc_predictive | Predictive shapes an SBC fitter reports |
| select_main_params | Select the "main" model parameters for diagnostic display |
| simulate.tulpa_fit | Simulate responses from a fitted tulpa model |
| smooth_effects | Extract fitted covariate smooths |
| sn_cdf | Skew-normal CDF |
| sn_match | Match three cumulants to a skew-normal parameterisation |
| sn_quantile | Skew-normal quantile |
| spatial | Areal spatially varying coefficient field |
| spatial_bym2 | BYM2 spatial structure |
| spatial_car | CAR / ICAR spatial structure |
| spatial_car_proper | Proper CAR spatial structure |
| spatial_gp | Gaussian process spatial structure (NNGP) |
| spatial_multiscale | Multi-scale Gaussian process spatial structure |
| spatial_range | Extract spatial range and variance from a fitted spatial... |
| spatial_rsr | Restricted spatial regression (RSR) |
| spatial_spde | SPDE spatial field (Matern via triangular mesh) |
| spatial_spde_custom | SPDE spatial field from custom matrices |
| spatial_svc | Spatially varying coefficient structure |
| spatiotemporal | Spatiotemporal interaction specifications for tulpa |
| spatiotemporal_effects | Extract spatiotemporal effects from fitted model |
| spatiotemporal_gp | Non-separable spatiotemporal GP |
| summary.tulpa_fit | Summarize and print a tulpa fit |
| svc | Extract spatially-varying coefficients from a fitted model |
| temporal | Extract temporal effects from a fitted model |
| temporal_ar | AR(p) temporal latent field (general-order autoregressive) |
| temporal_ar1 | AR1 temporal structure (first-order autoregressive) |
| temporal_ar2 | AR(2) temporal latent field (second-order autoregressive) |
| temporal_corr | Extract temporal correlation parameters from a fitted model |
| temporal_gp | Gaussian process temporal structure |
| temporal_multiscale | Multi-scale temporal structure |
| temporal_rtr | Restricted temporal regression (RTR) |
| temporal_rw1 | RW1 temporal structure (first-order random walk) |
| temporal_rw2 | RW2 temporal structure (second-order random walk) |
| temporal_tvc | Time-varying coefficient structure |
| test_dispersion | Test for over- or underdispersion |
| test_outliers | Test for outliers (simulation envelope) |
| test_uniformity | Test uniformity of PIT residuals |
| test_zero_inflation | Test for zero inflation |
| tgmrf | User-defined GMRF latent block |
| tgmrf_cpp | User-defined GMRF latent block, compiled C++ backend |
| tidy.tulpa_fit | Tidy fixed-effect table (broom-compatible) |
| tulpa | Fit a tulpa model |
| tulpa_bar_field_replicate | Replicate an areal graph across the levels of a factor... |
| tulpa_bar_field_specs | Expand a varying-coefficient bar into per-column field specs |
| tulpa_batched_pareto_k | Outer Pareto-k-hat for a batched-target grid-integrated fit |
| tulpa_build_model_data | Build model matrices from a parsed formula |
| tulpa_cache_clear | Remove compiled blocks from the tgmrf_cpp() cache |
| tulpa_cache_dir | Default cache directory for 'tgmrf_cpp()'-compiled DLLs |
| tulpa_check_control | Validate a 'control = list()' surface against its canonical... |
| tulpa_criteria | Model criteria from a pointwise log-likelihood |
| tulpa_diagnostics | Simulation-based diagnostics for tulpa models |
| tulpa_draws_array | Posterior draws as a 3D array |
| tulpa_eb | Empirical-Bayes random-effect covariances |
| tulpa_em_laplace | Fit a latent-variable model via EM + Laplace approximation |
| tulpa_em_mc | Generic Monte-Carlo EM driver |
| tulpa-envvars | Environment variables tulpa reads |
| tulpa_ep | Expectation-Propagation fit for a GLM |
| tulpa_family | Construct a minimal tulpa_family for simulation |
| tulpa_fit_summary | Build the summary of a tulpa fit around a coefficient table |
| tulpa_formula | Formula parsing for tulpa models |
| tulpa_gaussian | Fit a Gaussian linear model via tulpa's generic engine |
| tulpa_gibbs | Fit via Polya-Gamma Gibbs sampler |
| tulpa_grid_axis | Read a default nested-Laplace outer-grid axis |
| tulpa_grid_log_quad | Per-cell log quadrature weight of an outer grid |
| tulpa_hyper_check_copy_slab | Validate/default a copy-scale slab measure choice |
| tulpa_hyper_copy_slab_density | The copy-scale axis's PC-prior density |
| tulpa_hyper_draws | Hyperparameter draws from a nested-Laplace fit |
| tulpa_hyper_grid | Outer hyperparameter-grid integration with a user-supplied... |
| tulpa_hyper_grid_supports | Per-axis integrated support of an outer grid |
| tulpa_hyper_slice_home | Per-cell refinement tag of an outer grid |
| tulpa_integrator | Select the symplectic integrator for HMC and NUTS |
| tulpa_is_spatial_bar | Recognize an inline varying-coefficient bar |
| tulpa_iter_progress | Progress reporter for a counted R-side fitting loop |
| tulpa_joint_axis_specs_from_grid | Rebuild axis specs from an already-assembled outer grid |
| tulpa_joint_grid_batch | Fit multiple joint nested-Laplace models through one fused... |
| tulpa_joint_inner_vcov_blocks | Per-cell constrained inverse-precision sub-block for a joint... |
| tulpa_joint_inner_vcov_mixture | Outer-grid posterior covariance of a joint fit's latent... |
| tulpa_kfold | K-fold cross-validation for a tulpa fit |
| tulpa_laplace | Fit a model via Laplace approximation |
| tulpa_laplace_beta | Fit a beta-regression model via Laplace, estimating the... |
| tulpa_latent | Latent factor specification for unmeasured confounders |
| tulpa_loglik | Streaming pointwise log-likelihood |
| tulpa_multinomial | Multinomial (nominal K-class) logistic regression via Laplace |
| tulpa_nested_laplace | Nested Laplace approximation for latent Gaussian models |
| tulpa_nested_laplace_joint | Joint multi-likelihood nested Laplace approximation |
| tulpa_normalise_weights_safe | Normalise outer-grid log-marginals to posterior cell weights |
| tulpa_nuts_beta | Fit a beta-regression model via NUTS (joint sampling of beta... |
| tulpa_nuts_spde | Sample an SPDE GLM via NUTS, optionally jointly over Matern... |
| tulpa_ordinal | Ordinal (ordered K-class) cumulative-logit regression via... |
| tulpa_outer_grid | The outer hyperparameter grid of a nested-Laplace fit |
| tulpa-package | tulpa: Templated Unified Library for Posterior Approximation... |
| tulpa_parse_formula | Parse a mixed-model formula |
| tulpa_pit | Probability integral transform from a predictive CDF |
| tulpa_posterior_draws | Posterior draws from a nested-Laplace fit |
| tulpa_posterior_draws.tulpa_nested_laplace_joint | Posterior draws from a joint nested-Laplace fit |
| tulpa_powerscale_sensitivity | Power-scaling prior / likelihood sensitivity |
| tulpa_priors | Prior specification for tulpa models |
| tulpa_profile | Profile a fit by solver phase |
| tulpa_psis | Pareto-smoothed importance sampling |
| tulpa_re_aghq | Adaptive Gauss-Hermite refinement of a grouped random-effect... |
| tulpa_re_cov_gibbs | Gibbs estimation of random-effect covariances (exact-target... |
| tulpa_re_cov_nested | Nested-Laplace integration over random-effect covariances |
| tulpa_reloo | Selective refit of high-Pareto-k observations (reloo) |
| tulpa_rpg | Draw Polya-Gamma random variates |
| tulpa_simulate | Simulate data from a tulpa model |
| tulpa_spatial | Spatial structure specifications for tulpa |
| tulpa_spde_log_hyperprior | SPDE field hyperprior log density on (range, sigma) |
| tulpa_spde_precision_Q | Rebuild the SPDE/Matern field precision matrix |
| tulpa_temporal | Temporal structure specifications for tulpa |
| tulpa_tgmrf | Fit a custom tgmrf latent block |
| tulpa_theta_matrix | A fit's outer grid as a named matrix |
| tulpa_validate | Posterior predictive checks for tulpa models |
| tulpa_variogram | Empirical semivariogram of residuals |
| tvc | Extract temporally-varying coefficients from a fitted model |
| validate_gp | Validate a GP spatial specification against data |
| validate_mode | Validate that a fit used the expected mode |
| validate_temporal_multiscale | Validate a multi-scale temporal specification against data |
| VarCorr | Random-effect variances and correlations |
| vcov.tulpa_fit | Variance-covariance matrix of the fixed effects |
| wbic | Widely applicable Bayesian information criterion (WBIC) |
| with_tulpa_integrator | Run an expression under a chosen symplectic integrator |
