Skip to content

Commit

Permalink
Update readme file to include application to SOCPR
Browse files Browse the repository at this point in the history
  • Loading branch information
fhui28 committed Apr 25, 2024
1 parent 61b52d6 commit af35e87
Showing 1 changed file with 7 additions and 3 deletions.
10 changes: 7 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,15 +12,19 @@ This repository code contain template code associated with the manuscript "Spati

The following directories are currently available in this repository:

- `application_butterflies`, which contains template scripts to for reproducing the case study results for the Great Britain butterfly data in the manuscript. Also contained are:
- Two `cpp` scripts implementing independent factor analysis and spatial factor analysis/restricted spatial factor analysis (SFA/RSFA); these scripts are subsequently passed into [TMB](https://cran.r-project.org/web/packages/TMB/index.html) for model fitting;
- A subfolder `plots` that contains some of the plots available in the manuscript.
- `simulation`, which contains the following folders/documents for reproducing the simulation results in the manuscript:
- A `simdatfnv0.R` script that contains a function for simulating spatial multivariate abundance data from a joint species distribution model assuming some observed and some unobserved covariates;
- `binary_N400`, which contains two `R` scripts and two corresponding `cpp` scripts for reproducing the simulations involving binary responses, $N = 400$ spatial locations from the Great Britain butterfly data, and either coarse or fine-scaled observed covariates. The models compared include independent factor analysis, and spatial factor analysis/restricted spatial factor analysis (SFA/RSFA);
- `negin_N400`, which is set up analogously to the `binary_N400` folder except involving negative binomial count responses instead;
- `tweedie_N400`, which is set up analogously to the `binary_N400` folder except involving non-negative continuous responses from the Tweedie distribution instead;
- `simulationexample_coarsescaleX.pdf` and `simulationexample_finescaleX.pdf` which are the plots available in the manuscript demonstrating coarse or fine-scaled observed covariates, along with fine or coarse-scaled spatial errors forming the residual component of the unobserved covariates.
- `application_butterflies`, which contains template scripts to for reproducing the case study results for the Great Britain butterfly data in the manuscript. Also contained are:
- Two `cpp` scripts implementing independent factor analysis and spatial factor analysis/restricted spatial factor analysis (SFA/RSFA); these scripts are subsequently passed into [TMB](https://cran.r-project.org/web/packages/TMB/index.html) for model fitting;
- A subfolder `plots` that contains some of the plots available in the manuscript.
- `application_SOCPR`, which contains template scripts to for reproducing the case study results for the Southern Ocean Continuous Plankton Recorder survey data in the manuscript. Also contained are:
- Two `cpp` scripts implementing independent factor analysis and spatial factor analysis/restricted spatial factor analysis (SFA/RSFA); these scripts are subsequently passed into [TMB](https://cran.r-project.org/web/packages/TMB/index.html) for model fitting;
- A subfolder `plots` that contains some of the plots available in the manuscript.


The simulation results for $N = 1000$ can be produced by straightforwardly modifying the `R` scripts in the `simulation` folder.

Expand Down

0 comments on commit af35e87

Please sign in to comment.