https://github.com/mebrooks/growmod
An R package for fitting state-space models to repeated measures of multiple individuals with covariates
https://github.com/mebrooks/growmod
autoregressive-moving-average autoregressive-processes capture-recapture-data hidden-markov-model measurement-error missing-data non-stationary repeated-measures state-space-model timeseries tmb
Last synced: 10 months ago
JSON representation
An R package for fitting state-space models to repeated measures of multiple individuals with covariates
- Host: GitHub
- URL: https://github.com/mebrooks/growmod
- Owner: mebrooks
- Created: 2016-04-26T12:46:27.000Z (almost 10 years ago)
- Default Branch: master
- Last Pushed: 2023-01-27T12:51:25.000Z (almost 3 years ago)
- Last Synced: 2023-10-20T21:44:18.227Z (over 2 years ago)
- Topics: autoregressive-moving-average, autoregressive-processes, capture-recapture-data, hidden-markov-model, measurement-error, missing-data, non-stationary, repeated-measures, state-space-model, timeseries, tmb
- Language: R
- Size: 2.83 MB
- Stars: 6
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# growmod
### An R package for estimating growth using capture-recapture data of multiple individuals
This package fits growth models to capture-recapture data of individual sizes. Growth from one time to the next is modeled as a Markov process. Covariates such as environmental variables or individual variables can affect both the intercept and autoregressive parts of the model. Models can include random effects of individual, time, and birth cohort. Time must be in discrete steps. Observations of individual sizes can be missing, but covariates cannot be missing. Individual could represent an individual organism, population, or other unit of replication.
Estimation is done in a state-space framework using maximum marginal likelihood estimation via [Template Model Builder](https://github.com/kaskr/adcomp).
This package is part of a publication,
M E Brooks, C Clements, J Pemberton, and A Ozgul, "Estimation of Individual Growth Trajectories When Repeated Measures Are Missing," The American Naturalist 190, no. 3 (September 2017): 377-388. https://doi.org/10.1086/692797
## Installation
To install `growmod`, first install `TMB` from CRAN, then install `growmod` via
```
devtools::install_github("mebrooks/growmod/growmod", build_vignettes = TRUE)
```
You may need to install the `devtools` package, compiler tools, and other dependencies first. To install TMB, it may be necessary to install the version of Rtools that matches your version of R.
## Getting started
See `vignette("growmod")` for an example.
Before publishing results from models fit with `growmod`, we recommend that you check for potential bias using simulations as described in `vignette("sim_growmod")`.