Linear Latent Non-Gaussian Models with Flexible Distributions

Documentation for package ‘ngme2’ version 0.9.7

Help Pages

-- A --

adagrad	AdaGrad SGD optimization
adam	Adam SGD optimization
adamW	AdamW SGD optimization
adaptive_gd	Adaptive gradient descent
ar	ngme AR(p) model specification
ar1	ngme AR(1) model specification
argo_float	Argo float dataset
arma	ngme ARMA(p, q) model specification
arma11	Convenience wrapper for ARMA(1,1)

-- B --

batch_decay	Batch/checkpoint decay helper
batch_means_ci	Pooled Batch-Means Confidence Intervals from Multiple Chains
batch_means_estimator	Batch-Means Covariance Estimator for SGD Trajectories
bfgs	BFGS optimization
bv	Ngme bivariate model specification
bv_matern	Ngme bivariate model with Matern sub_models

-- C --

calibrate_inv_exp_lambda	Calibrate Inverse-Exponential Prior for NIG Driven Noise
calibrate_inv_exp_lambda_driven_nig	Calibrate Inverse-Exponential Prior for NIG Driven Noise
cienaga	The swamp of Cienaga Grande in Santa Marta, Colombia
cienaga.border	The x y location of the border of the swamp of Cienaga Grande in Santa Marta, Colombia
compare_noise_kld	Compare noise objects using Kullback-Leibler divergence
compute_index_corr_from_map	Helper function to compute the index_corr vector
compute_log_like	Compute Gaussian log-likelihood
compute_ngme_CI	Refit an Existing ngme Object with SGD and Compute Batch-Means CI
compute_ngme_ci	Refit an Existing ngme Object with SGD and Compute Batch-Means CI
compute_ngme_sgld_samples	Refit an Existing ngme Object with SGLD and Extract Samples
compute_score_given_pred	Compute the scores given the prediction
control_ngme	Generate control specifications for the ngme model
control_opt	Generate control specifications for 'ngme()' function.
control_opt_batch_ci	Generate CI-focused control settings for batch-means inference
create_paired_cv_splits	Create paired indices for bivariate cross-validation Ensures that paired observations (e.g., u_wind and v_wind at same location) are kept together in the same fold
cross_validation	Compute the cross-validation for the ngme model Perform cross-validation for ngme model first into sub_groups (a list of target, and train data)

-- D --

dgal	The Generalized Asymmetric Laplace (GAL) Distribution
dgig	The Generalised Inverse-Gaussian (GIG) Distribution
dig	The Inverse-Gaussian (IG) Distribution
digam	The Inverse-Gamma (IGam) Distribution
dnig	The Normal Inverse-Gaussian (NIG) Distribution

-- F --

f	Specifying a latent process model (wrapper function for each model)

-- G --

gal	The Generalized Asymmetric Laplace (GAL) Distribution
generic	Generic precision matrix operator
generic_ns	Non-stationary precision matrix operator with custom matrix combinations
get_data_from_formula	Extracts design matrix from a formula and data.
get_parameter_distance	Calculate parameter distance from true values
get_trace_trajectories	Get trace trajectories from ngme fitting
get_trajectories	get the trajectories of parameters of the model
gig	The Generalised Inverse-Gaussian (GIG) Distribution

-- I --

ig	The Inverse-Gaussian (IG) Distribution
igam	The Inverse-Gamma (IGam) Distribution
iid	ngme iid model specification

-- M --

make_time_series_cv_index	Create Time Series Cross-Validation Indices
matern	ngme Matern SPDE model specification
mean_list	taking mean over a list of nested lists
merge_noise	Merge 2 noise into 1 noise
merge_replicates	Merge model of replicates into model of 1 replicate given train_idx and test_idx, the merged model contains all the information of train_idx from different replicates.
momentum	Momentum SGD optimization

-- N --

name2fun	Convert transformation name to function
ngme	Fit an additive linear mixed effect model over replicates
ngme_as_sparse	Convert sparse matrix into sparse dgCMatrix
ngme_batch_ci	Batch-Means Confidence Intervals from an ngme Fit
ngme_cov_matrix	variance of the data or the latent field
ngme_make_mesh_repls	ngme make mesh for different replicates
ngme_model_types	Show ngme model types
ngme_noise	ngme noise specification
ngme_noise_types	Show ngme noise types
ngme_optimizers	List supported optimizers
ngme_parse_formula	Parse the formula for ngme function
ngme_post_samples	posterior samples of different latent models
ngme_prior_types	Show ngme priors
ngme_result	Access the result of a ngme fitted model
ngme_sgld_ci	Quantile Confidence Intervals from SGLD Samples
ngme_sgld_samples	Extract Posterior-like Samples from Stored SGLD Trajectories
ngme_ts_make_A	Make observation matrix for time series
ngme_update	Check whether a newer stable version of ngme2 is available
nig	The Normal Inverse-Gaussian (NIG) Distribution
noise_gal	ngme noise specification
noise_nig	ngme noise specification
noise_normal	ngme noise specification
noise_normal_nig	ngme noise specification
noise_skew_t	ngme noise specification
noise_t	ngme noise specification

-- O --

openmp_test	Test OpenMP availability and report the number of threads.
ou	Ornstein-Uhlenbeck Process Model

-- P --

pgal	The Generalized Asymmetric Laplace (GAL) Distribution
pgig	The Generalised Inverse-Gaussian (GIG) Distribution
pig	The Inverse-Gaussian (IG) Distribution
pigam	The Inverse-Gamma (IGam) Distribution
plot.ngme_noise	Plot the density of one or more stationary noise objects
plot.ngme_sgld_ci	Plot Posterior Distributions from SGLD Samples
plot.parameter_distance	Plot method for parameter_distance
pnig	The Normal Inverse-Gaussian (NIG) Distribution
poly_decay	Polynomial schedule helper
posterior_plot	Plot Posterior Distributions from SGLD Samples
precision_matrix_multivariate	Compute the precision matrix for multivariate model
precision_matrix_multivariate_spde	Compute the precision matrix for multivariate spde Matern model
precond_sgd	Preconditioner SGD optimization
predict.ngme	Predict function of ngme2 predict using ngme after estimation
print.ngme	Print an ngme model
print.ngme_model	Print ngme model
print.ngme_noise	Print ngme noise
print.ngme_operator	Print ngme operator
print.ngme_replicate	Print ngme object
print.ngme_trajectories	Print method for ngme_trajectories
print.noise_kld_comparison	Print method for noise_kld_comparison
print.parameter_distance	Print method for parameter_distance
priors	Prior Container
prior_half_cauchy	Prior Half-Cauchy
prior_inv_exp	Prior Inverse-Exponential
prior_inv_exponential	Prior Inverse-Exponential
prior_none	Prior None
prior_normal	Prior Normal
prior_pc_sd	Prior PC-SD

-- Q --

qgal	The Generalized Asymmetric Laplace (GAL) Distribution
qgig	The Generalised Inverse-Gaussian (GIG) Distribution
qig	The Inverse-Gaussian (IG) Distribution
qigam	The Inverse-Gamma (IGam) Distribution
qnig	The Normal Inverse-Gaussian (NIG) Distribution

-- R --

re	ngme random effect model
rgal	The Generalized Asymmetric Laplace (GAL) Distribution
rgig	The Generalised Inverse-Gaussian (GIG) Distribution
rig	The Inverse-Gaussian (IG) Distribution
rigam	The Inverse-Gamma (IGam) Distribution
rmsprop	Root Mean Square Propagation (RMSProp) SGD optimization
rnig	The Normal Inverse-Gaussian (NIG) Distribution
rw1	Random Walk Model of Order 1 (RW1)
rw2	Random Walk Model of Order 2 (RW2)

-- S --

sgd	Vanilla SGD optimization
sgld	Stochastic Gradient Langevin Dynamics (SGLD) optimization
simulate.ngme	Simulate from a ngme object (possibly with replicates)
simulate.ngme_model	Simulate latent process with noise
simulate.ngme_noise	Simulate ngme noise object
spacetime	Ngme space-time non-separable model specification
stepsize_control	Unified stepsize control
stepsize_decay	Stepsize decay schedule
stepsize_schedule	Stepsize schedule
summary.ngme	Summary of ngme fit result
summary.ngme_batch_ci	Summary for Batch-Means CI Results

-- T --

tp	ngme tensor-product model specification
traceplot	Trace plot of ngme fitting

-- V --

var1	ngme VAR(1) bivariate model specification (Cayley re-parameterization)