Module 4

Key topics

• Poisson regression
• Logistic regression
• Generalised linear models
• Generalised linear mixed-effects models

“Ecology has increasingly become a data- and model-centric discipline…”

— Trends in ecology and conservation over eight decades

R packages and datasets

It is assumed in all following examples of this module that the following code has been executed successfully.

packages used in this module

library(tidyverse) ## general functionality
library(lme4) ## mixed effects models

datasets used in this module

base_url <- "https://raw.githubusercontent.com/STATS-UOA/databunker/master/data/"

1. birds⁸

birds <- read_delim(paste(base_url, "bird_abundance.csv", sep = "")) %>%
  dplyr::select(c("OliveFarm","Management","Turdus_merula","Phylloscopus_collybita")) %>%
  pivot_longer(., c(-OliveFarm, -Management), names_to = "Species", values_to = "Count") 

2. lobster⁹

lobster <- read_csv(paste(base_url, "lobster.csv", sep = ""))

3. mice¹⁰

mice <- read_csv(paste(base_url, "autism.csv", sep = ""))

---

8. Source: Partitioning beta diversity to untangle mechanisms underlying the assembly of bird communities in Mediterranean olive groves↩︎

9. Source: Influence of predator identity on the strength of predator avoidance responses in lobsters.↩︎

10. Source: Human Gut Microbiota from Autism Spectrum Disorder Promote Behavioral Symptoms in Mice↩︎