Bayesian Priors for Matrix Population Models

Provides functions to correct biased transition and fertility estimates in population projection matrices caused by small sample sizes. Small or short-term studies frequently produce structural zeros (biologically possible transitions never observed) and structural ones (transitions estimated at 100% survival, stasis, or mortality that are biologically implausible). Both distort matrix structure and bias estimates of population growth. Implements a multinomial-Dirichlet Bayesian prior for transition probabilities and a Gamma-Poisson prior for reproduction, allowing analysts to incorporate prior biological knowledge and regularise estimates from rare or unobserved events. Includes functions to compute marginal posterior credible intervals for all transition probabilities (transition_CrI()), visualise those intervals as point-range plots (plot_transition_CrI()), and display the full posterior beta density for each matrix entry (plot_transition_density()). Methods are described in Tremblay et al. (2021) .

raretrans

Functions to create matrix population models from a combination of data on stage/age transitions and Bayesian prior information. This compensates for structural problems caused by missing observations of rare transitions (“holey matrices”).

Based on methods described in:

Tremblay, R. L., Tyre, A. J., Pérez, M.-E., & Ackerman, J. D. (2021). Population projections from holey matrices: Using prior information to estimate rare transition events. Ecological Modelling, 447, 109526. https://doi.org/10.1016/j.ecolmodel.2021.109526

Requirements

• R >= 4.1.0
• Core package dependencies: ggplot2, rlang
• Vignette dependencies: tidyverse, popbio, huxtable, popdemo, googledrive

Note: The core functions work on any R >= 4.1.0. Vignettes require R >= 4.1.0 due to dependencies in popdemo, dplyr, and purrr. If you are on an older version of R, install without vignettes (see below) and read them online at https://atiretoo.github.io/raretrans/.

Installation

Install the stable release from CRAN:

install.packages("raretrans")

Or install the development version from GitHub:

# install.packages("remotes")  # if needed
remotes::install_github("atiretoo/raretrans")

The code and data used to produce the published paper are tagged v1.0.0:

remotes::install_github("atiretoo/[email protected]")

Overview

The main functions in this package are:

All functions take a TF list of two matrices as their first argument: a transition matrix T and a fertility matrix F. These can be constructed by hand or created with popbio::projection.matrix(..., TF = TRUE) from individual-level transition data.

Interactive Application

raretrans includes an interactive Shiny application to explore the effects of different Bayesian priors on transition matrices dynamically.

raretrans::run_app()

Quick Start

library(raretrans)

# Example with *Lepanthes eltoroensis* data included in the package
data(L_elto)

# Build a TF list from individual transition data
TF <- popbio::projection.matrix(L_elto, TF = TRUE)

# Fill structural zeros and perfect (1.0) survival, 
# transitions, stasis and fertilities using uninformative priors
fill_transitions(TF)
fill_fertility(TF)

Vignettes

Browse all vignettes at https://atiretoo.github.io/raretrans/.

Getting Help

• Report bugs or request features at https://github.com/atiretoo/raretrans/issues
• Read the full function reference at https://atiretoo.github.io/raretrans/reference/

Reference

Caswell, H. (2001). Matrix Population Models: Construction, Analysis, and Interpretation (2nd ed.). Sinauer Associates.

Code of Conduct

Please note that the raretrans project is released with a Contributor Code of Conduct. By contributing to this project, you agree to abide by its terms.