BI3010: STATISTICAL ANALYSIS OF BIOLOGICAL DATA (2025-2026)

This course introduces students to modern statistical modelling in the context of the biological and environmental sciences. Rather than focusing on individual tests or formulas, the course follows a statistical workflow, from data exploration and model specification to interpretation, communication, and critique. Emphasis is placed on understanding the assumptions, limitations, and responsibilities involved when analysing data.

Students will build a strong foundation in linear models and related techniques, learning how to assess model fit, interrogate results, and visualise findings using R and ggplot2. The course also encourages critical thinking about statistical practices.

By the end of the course, students will be able to:

• Explore and critically evaluate data to guide model development;
• Analyse and interpret a variety of linear and generalised linear models;
• Critically evaluate the validity of assumptions made both of data and of models;
• Communicate statistical results clearly using effective visualisation and reporting.

This course aims to instil a robust approach to statistical analysis. By engaging with a series a lectures and podcasts, completing a set of exercises that progressively add more complexity, you will learn how:

1.  To conduct data exploration and determine an appropriate approach to data analysis;
2.  To analyse a variety of types of data and interpret results from a range of analyses, and
3.  To present the results from the analyses in an appropriate manner.

At the end of the course, students will be able to:conduct data exploration and determine an appropriate approach to data analysis;

• analyse, interpret and present results from a variety of linear modelling analyses;
• explain the strengths and weaknesses of different sampling designs;
• characterise robust and reproducible research practices that relate to sampling, hypothesis testing and statistical analysis;.

Topics covered in the course include:

• Why do we need statistics?
• Data visualisation theory and effective figure creation
• Introduction to linear models (LMs) and model assumptions
• LMs with continuous and categorical predictors
• Model interpretation and assumption checking
• Multiple predictors, confounding, and causality
• Null Hypothesis Significance Testing and p-values
• Information-theoretic approaches (e.g., AIC)
• Introduction to Generalised Linear Models (GLMs), including Poisson GLMs

Information on contact teaching time is available from the course guide.

More Information about Week Numbers