Description

The purpose of this course is to train students in the quantitative skills they need to undertake data analysis and hypothesis testing in biology. These skills include programming to support data handling, exploration and visualization as well as fundamental statistical modelling training to undertake quantitative hypothesis testing.

The course places a strong emphasis on critical thinking about data and hypothesis development and testing – i.e. the "doing" of biology.

Students will explore the nature of biological data by learning to explore, groom, visualize and analyse data with a critical eye grounded in biological theory. In all cases, data analysis skills will be performed through the free and open-source programming language R.

Students will learn:

Basic programming functions and computational thinking.
Data exploration and quality control tools.
Data management and manipulating data objects
Data visualization
To relate data to biological theory to critically analyse data and develop data models

Students will learn statistical modelling concepts and how they can be used to test hypotheses. In all cases, statistical skills learning will be motivated and framed within a hypothesis-testing context. This will allow students to relate their own hypothesis testing to biological theory, and apply the methods learned in class for future hypothesis testing tasks. Students will be trained in a statistical modelling framework that they can use to move from research hypothesis to statistical modelling and results. This flexible process is extendable and intuitive and can be applied to assess hypotheses common to biology and beyond.

Students will learn to:

identify and communicate their research question as the variation they are trying to explain and the motivations behind it
formulate and communicate their research hypothesis, mechanistically based and grounded in biological theory
build robust statistical models to inform their experimental design and ultimately model their hypothesis
think critically about and assess their model choices and assumptions and communicate the limitations of their model
quantify the patterns and likelihood of the underlying relationships through model selection
report the results of their hypothesis testing including variation explained, significant relationships and their patterns
visualize their hypothesis testing results including modelled patterns, uncertainty, and data
use their model results to make predictions, and understand the limitations and uncertainty when doing so.

Learning outcomes and competences:

At the end of the course, the student is expected to be able to

Manage, manipulate, and visualize biological data in R.
Critically analyse biological data in R.
Apply an end-to-end hypothesis-testing framework
communicate a biological research question and underlying motivation,
communicate a research hypothesis and mechanistic biological foundation,
describe and assess the data available to test a hypothesis,
identify and build a robust statistical model tailored to a hypothesis,
assess the performance and usefulness of the statistical model, and
report results in a meaningful and transparent way
Communicate data analysis and hypothesis testing in a written biological report format.
Course period31/01/2023 → …
Course levelBachelor level
Course format10