In greta-dev/greta: Simple and Scalable Statistical Modelling in R

Logistic regression

A simple logistic regression being to estimate the probability of species presence along a number of environmental gradients.

data

# make fake data
n_env <- 3
n_sites <- 20

# n_sites x n_env matrix of environmental variables
env <- matrix(rnorm(n_sites * n_env), nrow = n_sites) 
# n_sites observations of species presence or absence
occupancy <- rbinom(n_sites, 1, 0.5)

greta code

alpha <- normal(0, 10)
beta <- normal(0, 10, dim = n_env)

# logit-linear model
linear_predictor <- alpha + env %*% beta
p <- ilogit(linear_predictor)

# distribution (likelihood) over observed values
distribution(occupancy) <- bernoulli(p)