This module provides training in statistics for environmental scientists. We emphasize the use of software to analyze real environmental data. We do not assume extensive prior knowledge. We will teach the essential theory alongside the practical components.

(LO1) Make sense of the statistical terms that appear in scientific papers and the media

(LO2) Summarize data using graphs, tables, and numerical summaries

(LO3) Choose appropriate statistical methods to answer research questions

(LO4) Use statistical software to apply these methods, and interpret the output

(S1) Problem solving skills

(S2) Numeracy

(S3) IT skills

In this module, students will first be taught the concepts underlying statistical analysis and how to summarise data, before exploring different methods of analysis and how they are appropriate for different scientific questions. Alongside information on statistical analysis, students will learn how to use the industry standard software R through the use of the RStudio environment. Teaching takes a blended approach with theory and explanations presented via online asynchronous lectures, and practice achieved in weekly supervised workshops. The main topics to be covered are:

Graphical and numerical summaries of data
Probability distributions and the normal distribution

Samples, populations and the Central Limit Theorem
Confidence intervals

Hypothesis tests
t-tests

One-way analysis of variance
Two-way analysis of variance

Correlation
Regression

General linear models

Two-way tables
Goodness of fit

Design ing surveys and experiments
Choosing analyses

Nonparametric statistics

The module will be delivered by a combination of in-person computer workshops, weekly live in-person help-sessions, and non-timetabled activities delivered through the VLE. Students will explore data and statistical analysis through e-lectures, in combination with additional reading, with support available through Discussion Boards. E-lectures will provide students with the theoretical background to statistical analysis, and will demonstrate the use of important methods of analysis alongside relevant examples to provide context. In face-to-face workshops, students will have an opportunity to generate data and attempt analyses themselves with support from teaching staff. The workshops will provide an environment in which students can get comfortable with the coding environment (R and RStudio), work and experiment with code, and develop a working appreciation of data manipulation and analysis. Additional live help-sessions will explore particularly challenging topics and allow for st udents to raise issues and difficulties, whilst providing further context and examples of the work being undertaken.
The module therefore utilises a blended learning approach, requiring students to familiarise themselves with material outside of classes before putting their understanding to practice with real data in timetabled workshops. Tasks set in workshops provide opportunities for active learning, and the use of industry-standard software and engagement with the VLE improve student digital fluency.