FW 8051: Statistics for Ecologists
Course description
Ecological data pose many challenges to statistical inference. Most data come from observational studies rather than designed experiments; observational units are frequently sampled repeatedly over time, resulting in multiple, non-independent measurements; response data are often binary (e.g., presence-absence data) or non-negative integers (e.g.., counts), and therefore, the data do not fit the standard assumptions of linear regression (Normality, constant variance). This course will familiarize students with modern statistical methods that address these complexities, with an emphasis on Bayesian implementations of commonly used regression models. We will begin with a review of linear regression, emphasizing the role of design matrices in model construction. We will learn how to create explanatory variables (e.g., when fitting models with categorical predictors) and also generate model-based estimates of predicted values along with associated measures of uncertainty. With this foundation in place, we will then consider extensions to non-Normal data (e.g., generalized linear models) and correlated data (mixed models, generalized estimating equations). Exercises will utilize program R and general Bayesian modeling software JAGs and will make extensive use of both real and simulated data sets.
Course resources
- Current course syllabus
- We use an open-source textbook that I developed specifically for the course.
- I also developed a companion exercise book.