SpatialDeltaGLMM Is an R package for implementing a spatial delta-generalized linear mixed model (delta-GLMM) for use when standardizing fishery-independent index data for U.S. West Coast surveys. Has built in diagnostic functions and model-comparison tools Is intended to improve analysis speed, replicability, peer-review, and interpretation of index standardization methods Will eventually be improved to incorporate informative help files accessible via standard R commands.
Background This tool is designed to estimate spatial variation in density using fishery-independent data, with the goal of estimating total abundance for a target species in one or more years. The model builds upon delta-generalized linear mixed modelling techniques (Thorson and Ward 2013,2014), which separately models the proportion of tows that catch at least one individual ("encounter probability") and catch rates for tows with at least one individual ("positive catch rates"). Submodels for encounter probability and positive catch rates always incorporate variation in density among years (as a fixed effect), and can incorporate variation among sampling vessels (as a random effect, Thorson and Ward 2014). Each submodel can also estimate spatial variation (variation that is constant among years), and spatiotemporal variation (variation over space which differs among years). Spatial and spatiotemporal variation are approximated as Gaussian Markov random fields (Thorson Skaug et al. 2015 ICESJMS), which imply that correlations in spatial variation decay as a function of distance. The tool incorporates geometric anisotropy, i.e., differences and rotation of the direction of correlation, where correlations may decline faster inshore-offshore than alongshore (Thorson Shelton et al. 2015 ICESJMS).
SpatialDeltaGLMM now has unit-testing to ensure that results are consistent across software updates
VAST (link here) has been developed as a multispecies extension to
SpatialDeltaGLMM, and unit testing confirms that it gives identical results when using data for a single species. I recommend that new users use
VAST to ease the transition to multispecies or age/size-structured index models.
* Other spatio-temporal tools are linked at www.FishStats.org
There are three main resources for learning about and using the tool:
Please see the tutorial for example code.
Please use the R help files, e.g., model settings are documented in
?SpatialDeltaGLMM::Data_Fn after you have installed the package
Other resources include:
You should browse abstracts and read relevant papers
You can join the FishStats listserv
You can post questions on the issue tracker but please first confirm that your question isn't answered elsewhere.
Regions that have been previously tested (and have associated meta-data):
and see FishViz.org for visualization of results for regions with a public API for their data, using package
FishData (link here).
This function depends on R version >=3.1.1 and a variety of other tools.
First, install the package
devtools package from CRAN
# Install and load devtools package install.packages("devtools") library("devtools")
Note: at the moment, packages
INLA can be installed using the commands
# devtools command to get TMB from GitHub install_github("kaskr/adcomp/TMB") # source script to get INLA from the web source("http://www.math.ntnu.no/inla/givemeINLA.R")
Next, please install package
SpatialDeltaGLMM from this GitHub repository using a function in the
# Install package install_github("nwfsc-assess/geostatistical_delta-GLMM", ref="3.3.0") # Load package library(SpatialDeltaGLMM)
Or you can always use the development version
# Install package install_github("nwfsc-assess/geostatistical_delta-GLMM")
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.