In poissonconsulting/jmbr: Analyses Using JAGS

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "tools/README-"
)

jmbr

Introduction

jmbr (pronounced jimber) is an R package to facilitate analyses using Just Another Gibbs Sampler (JAGS).

It is part of the mbr family of packages.

Demonstration

library(jmbr)
library(mbr)

# define model in JAGS language
model <- model("model {
  alpha ~ dnorm(0, 10^-2)
  beta1 ~ dnorm(0, 10^-2)
  beta2 ~ dnorm(0, 10^-2)
  beta3 ~ dnorm(0, 10^-2)

  log_sAnnual ~ dnorm(0, 10^-2)
  log(sAnnual) <- log_sAnnual

  for(i in 1:nAnnual) {
    bAnnual[i] ~ dnorm(0, sAnnual^-2)
  }

  for (i in 1:length(Pairs)) {
    log(ePairs[i]) <- alpha + beta1 * Year[i] + beta2 * Year[i]^2 + beta3 * Year[i]^3 + bAnnual[Annual[i]]
    Pairs[i] ~ dpois(ePairs[i])
  }
}")

# add R code to calculate derived parameters
model <- update_model(model, new_expr = "
for (i in 1:length(Pairs)) {
  log(prediction[i]) <- alpha + beta1 * Year[i] + beta2 * Year[i]^2 + beta3 * Year[i]^3 + bAnnual[Annual[i]]
}")

# define data types and center year
model <- update_model(model, 
  select_data = list("Pairs" = integer(), "Year*" = integer(), Annual = factor()),
  derived = "sAnnual",
  random_effects = list(bAnnual = "Annual"))

data <- bauw::peregrine
data$Annual <- factor(data$Year)

set_analysis_mode("report")

# analyse
analysis <- analyse(model, data = data)
analysis <- reanalyse(analysis)

coef(analysis, simplify = TRUE)

plot(analysis)

# make predictions by varying year with other predictors including the random effect of Annual held constant
year <- predict(analysis, new_data = "Year")

# plot those predictions
library(ggplot2)

ggplot(data = year, aes(x = Year, y = estimate)) +
  geom_point(data = bauw::peregrine, aes(y = Pairs)) +
  geom_line() +
  geom_line(aes(y = lower), linetype = "dotted") +
  geom_line(aes(y = upper), linetype = "dotted") +
  expand_limits(y = 0)

Installation

To install from GitHub

install.packages("devtools")
devtools::install_github("poissonconsulting/jmbr")

Citation

citation(package = 'jmbr')

Contribution

Please report any issues.

Pull requests are always welcome.

Code of Conduct

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

Inspiration

• jaggernaut

poissonconsulting/jmbr documentation built on Jan. 18, 2024, 1:09 a.m.