Skip to content

Course Schedule

Day 1: Foundations & Unsupervised Methods

Focus: Understanding data structure and discovering patterns without predefined groups

Time Topic Materials
09:15–09:45 Welcome & Why Multivariate Statistics? Page
09:45–10:45 Correlation, Covariance & Multicollinearity Page CorCov / Page Multi
10:45–11:00 🪫 -Break-> 🔋
11:00–12:15 Clustering Methods Page
12:15–13:15 🍕 Lunch
13:15–14:30 Principal Component Analysis (PCA) Page
14:30–14:45 🪫 -Break-> 🔋
14:45–16:15 Ordination (NMDS/PCoA) Page
16:15–16:30 Day 1 Wrap-up & Q&A (+ intro to CCA if time allows)

Learning Objectives

By the end of Day 1, you will be able to:

  • Understand and interpret correlation and covariance matrices
  • Recognise and handle multicollinearity in your data
  • Use hierarchical and k-means clustering to find groups
  • Apply PCA to reduce dimensionality and visualise patterns
  • Perform NMDS and PCoA ordination
  • Choose appropriate distance metrics for your data type

Day 2: Supervised & Constrained Methods

Focus: Predicting group membership and linking community patterns to environmental drivers

Time Topic Materials
09:00–10:30 Linear Discriminant Analysis (LDA) Page
10:30–10:45 🪫 -Break-> 🔋
10:45–12:15 Logistic Regression Page
12:15–13:15 🥙 Lunch
13:15–14:30 PERMANOVA Page
14:30–14:45 🪫 -Break-> 🔋
14:45–16:00 Constrained Ordination (RDA/CCA) Page
16:00–16:30 Method Selection & Course Wrap-up Decision Guide

Learning Objectives

By the end of Day 2, you will be able to:

  • Classify samples using LDA and interpret discriminant functions
  • Build and validate logistic regression models
  • Test for group differences in multivariate space using PERMANOVA
  • Use constrained ordination (RDA/CCA) to relate community composition to environmental variables
  • Select the appropriate method for your own research question

What to Bring

  • Laptop with R (≥ 4.0) and RStudio installed
  • R packages installed in advance (see R Setup & Basics)
  • Power adapter (limited outlets available)

See you end of March!