Replicate analysis from: tinyVAST: R package with an expressive interface to specify lagged and simultaneous effects in multivariate spatio-temporal models

Published Apr 07, 2025 on Dryad. https://doi.org/10.5061/dryad.rv15dv4fv

Data files

Apr 07, 2025 version files 15.87 MB

Abstract

Aim

Multivariate spatio-temporal models are widely applicable, but specifying their structure is complicated and may inhibit wider use. We introduce the R package tinyVAST from two viewpoints: the software user and the statistician.

Innovation

From the user viewpoint, tinyVAST adapts a widely used formula interface to specify generalized additive models, and combines this with arguments to specify spatial and spatio-temporal interactions among variables. These interactions are specified using arrow notation (from structural equation models), or an extended arrow-and-lag notation that allows simultaneous, lagged, and recursive dependencies among variables over time. The user also specifies a spatial domain for areal (gridded), continuous (point-count), or stream-network data. From the statistician's viewpoint, tinyVAST constructs sparse precision matrices representing multivariate spatio-temporal variation, and parameters are estimated by specifying a generalized linear mixed model (GLMM). This expressive interface encompasses vector autoregressive, empirical orthogonal functions, spatial factor analysis, and ARIMA models.

Main conclusion

To demonstrate, we fit the data from two survey platforms sampling corals, sponges, rockfishes, and flatfishes in the Gulf of Alaska and Aleutian Islands. We then compare eight alternative model structures using different assumptions about habitat drivers and survey detectability. Model selection suggests that towed-camera and bottom trawl gears have spatial variation in detectability but sample the same underlying density of flatfishes and rockfishes, and that rockfishes are positively associated with sponges while flatfishes are negatively associated with corals. We conclude that tinyVAST can be used to test complicated dependencies representing alternative structural assumptions for research and real-world policy evaluation.

https://doi.org/10.5061/dryad.rv15dv4fv

Code and data required to replicate analyses.

Description of the data and file structure

Data files include:

goaai_outline.xxx – files with extensions “.shp”, “.dbf”, “.prj”, and “.shx” representing a shapefile with the spatial domain for the case-study example using projection CRS “+proj=natearth +lon_0=-170 +x_0=0 +y_0=0 +datum=WGS84 +units=km +no_defs”
Formatted_data.csv – A CSV containing all data used in the case study analysis. This contains the following columns:

Categorical variable “Year”: with values “camera” (for when the camera survey was conducted), or “1990-2019” (indicating the calendar year for bottom trawl surveys)
Integer variable “Count”: indicating the count of a given taxon in that sample
Categorical variable “Group4”: with six levels, indicating whether the sample was “Coral” and “Sponge” (corals and sponges in the camera survey), “Flat” and “Rock” (aggregated flatfishes and rockfishes in the camera survey), or “Flat” and “Rock” (aggregated flatfishes and rockfishes in the bottom trawl survey)
Numeric variable “X”: Location for sample in X coordinates using same projection as shapefile
Numeric variable “Y”: Location for sample in Y coordinates using same projection as shapefile
Numeric variable “depth_km”: Depth for the seafloor at the location of the sample, in km
Numeric variable “AreaSwept”: Area swept by a sample in Hectares
Categorical variable “time”: Dummy column with single level “constant”

Sharing/Access information

Code and data versions are publicly available:

See “Formatted_data.csv” described above.
See “Code/Software” section below.

Data was derived from the following sources:

The Gulf of Alaska and Aleutian Islands bottom trawl survey conducted by the Alaska Fisheries Science Center
The Deep Sea Coral drop camera survey conducted by the Alaska Fisheries Science Center

Code/Software

Code files include:

Reprex_code_R1.R – An R script that can replicate analyses
tinyVAST_1.0.0.zip – A copy of the R-package required, which includes LICENCE information. Up to date versions are available via CRAN (https://cran.r-project.org/web/packages/tinyVAST/index.html) and GitHub (https://github.com/vast-lib/tinyVAST)