30 March 2026

Who am I?

My role as course instructor

  • Help you learn the material
  • Help you learn how to ask for help
  • Be a future resource

Who are you?

Introduce yourself

  1. Your degree program (MS, PhD)

  2. Your school/department

  3. Your area of study (a phrase or short sentence)

What is this course about?

Two major goals in ecology:

1. Infer process from pattern

Process \(\overset{?}{\Rightarrow}\) Pattern

Pattern \(= f(\)Process\()\)

Data \(= f(\)Process\()\)

Data = Process + Noise

Ecological data often have lots of noise

Barplot comparing the proportions of signal and noise in contrasting datasets between ecology and finance.

Our challenge is to separate
the signal from the noise

Two major goals in ecology:

1. Infer process from pattern

2. Make predictions

Ecological forecasting

How will [some future scenario] affect [some ecosystem service]?

General approach

Question \(\rightarrow\) Data \(\rightarrow\) Model \(\rightarrow\) Inference \(\rightarrow\) Prediction

Forms of linear models

Errors Single random process Multiple random processes
Normal Linear Model (LM) Linear Mixed Model (LMM)
Non-normal Generalized Linear Model (GLM) Generalized Linear Mixed Model (GLMM)

Forms of linear models

Circle and arrow diagram showing the relationtships between general and generalized linear models with and without random effects.

Learning objectives for the course

By the end of the quarter, students should be able to:

  • Identify an appropriate statistical model based on the data and specific question

  • Understand the assumptions behind a chosen statistical model

  • Use R to fit a variety of linear models to data

  • Evaluate data support for various models and select the most parsimonious model among them

  • Use R Markdown to combine text, equations, code, tables, and figures into reports

Software

R Software

An environment for statistical computing and graphics

R Software

  • Most of R’s current capabilities come from packages
  • We will use several different packages for fitting statistical models (eg, nlme, lme4)

RStudio

An integrated development environment (IDE) for R

 

RStudio highlights

  • Syntax highlighting, code completion, smart indentation
  • Easily manage multiple working directories using projects
  • Interactive debugger to diagnose and fix errors quickly
  • Extensive package development tools
  • Built-in tools & GUIs for git & Markdown

RStudio benefits

 

R Markdown

Notebook interface to weave together text, equations, and code into nicely formatted output

Allows you to create and document fully reproducible workflows

Ideal framework for homework assignments!

R Markdown

Supports dozens of static and dynamic output formats

  • HTML
  • PDF
  • MS Word
  • HTML5 slides
  • Books
  • Shiny apps
  • Scientific articles
  • websites

Gallery here