Learn R Programming

tinyVAST (version 1.5.0)

Multivariate Spatio-Temporal Models using Structural Equations

Description

Fits a wide variety of multivariate spatio-temporal models with simultaneous and lagged interactions among variables (including vector autoregressive spatio-temporal ('VAST') dynamics) for areal, continuous, or network spatial domains. It includes time-variable, space-variable, and space-time-variable interactions using dynamic structural equation models ('DSEM') as expressive interface, and the 'mgcv' package to specify splines via the formula interface. See Thorson et al. (2025) for more details.

Copy Link

Version

Install

install.packages('tinyVAST')

Monthly Downloads

790

Version

1.5.0

License

GPL-3

Maintainer

James Thorson

Last Published

March 23rd, 2026

Functions in tinyVAST (1.5.0)

make_eof_ram

Make a RAM (Reticular Action Model)
sanity

Sanity check of a tinyVAST model
sample_variable

Sample from predictive distribution of a variable
tinyVASTcontrol

Control parameters for tinyVAST
predict.tinyVAST

Predict using vector autoregressive spatio-temporal model
print.tinyVAST

print summary of tinyVAST model
tinyVAST

Fit vector autoregressive spatio-temporal model
logLik.tinyVAST

Extract the (marginal) log-likelihood of a tinyVAST model
red_snapper_shapefile

Shapefile for red snapper analysis
sea_ice

Arctic September sea ice concentrations
make_sem_ram

Make a RAM (Reticular Action Model) from a SEM (structural equation model)
red_snapper

Presence/absence, count, and biomass data for red snapper
residuals.tinyVAST

Calculate deviance or response residuals for tinyVAST
parse_path

Parse path
spatial_cor

Approximate spatial correlation
simulate_sfnetwork

Simulate GMRF for stream network
sfnetwork_evaluator

Construct projection matrix for stream network
get_data.tinyVAST

Get data
red_grouper_diet

Data to demonstrate model-based diet proportions
sfnetwork_mesh

Make mesh for stream network
project

Project tinyVAST to future times (EXPERIMENTAL)
simulate.tinyVAST

Simulate new data from a fitted model
rmvnorm_prec

Multivariate Normal Random Deviates using Sparse Precision
summary.tinyVAST

summarize tinyVAST
reload_model

Reload a previously fitted model
rotate_pca

Rotate factors to match Principal-Components Analysis
vcov.tinyVAST

Extract Variance-Covariance Matrix
deviance_explained

Calculate deviance explained
salmon_returns

North Pacific salmon returns
reexports

Objects exported from other packages
term_covariance

Extract covariance
add_predictions

Add predictions to data-list
cAIC

Calculate conditional AIC
add_mesh_covariates

Add mesh covariates to vertices and triangles
bering_sea

Survey domain for the eastern and northern Bering Sea surveys
GetResponse.tinyVAST

Get response
bering_sea_capelin_forecasts

Data to demonstrate probabilistic forecasting
bering_sea_pollock_vast

Estimated proportion-at-age for Alaska pollock using VAST
bering_sea_pollock_ages

Survey catch-rates at age for Alaska pollock in the Eastern and Northern Bering Sea
atlantic_yellowtail

Northwest Atlantic yellowtail
alaska_sponge_coral_fish

Data to analyze sponge-coral-fish associations
make_dsem_ram

Make a RAM (Reticular Action Model)
classify_variables

Classify variables path
condition_and_density

Condition and density example
conditional_gmrf

Conditional simulation from a GMRF
Families

Additional families
integrate_output

Integration for target variable