Overview

This module takes students from the basic principles of designing research questions and gathering samples of data, through to advanced skills in managing, visualising and interrogating data using statistical tests. These essential skills are needed across disciplines involved in natural resource management and conservation, from biology to the social sciences. The course is taught using Microsoft Excel, the free statistical programming language R, and the RStudio integrated development environment. These are used for data science in multiple sectors and industries, enabling flexible and repeatable data handling, visualisation and statistical testing workflows. Running themes throughout the module include: tackling “mathsphobia” and reducing anxiety around programming and quantitative data analysis, and learning how to tackle programming problems independently. Topics may include: How does using data help us tell stories about the world? Examples of data uses and misuses; Principles of sampling from populations; What are statistical tests and why do we need them?; Working with R for data management, exploration and visualisation; Principles of tidy data; Data distributions, sample sizes, and basic statistical tests in R; Multiple linear regression and mixed effects models; How to explore new methods for data analysis in R – beyond linear models.

Assessment Strategy

Threshold - A threshold student should have a basic knowledge of how to read an existing dataset into R, calculate descriptive statistics, produce basic data visualisations using default settings, apply basic statistical tests appropriately, and attempt interpretation.

Assessment 1: complete a pre-prepared template for a quantitative analysis write-up using only descriptive statistics and data visualisation: student completes all sections of the template and attempts interpretation.

Assessment 2: Mini-paper on own research question and data or pre-prepared question and provided dataset in R (specified format: very short introduction, data collection and analytical methods fully explained, detailed results section including data visualisation in R, conclusions). All R code used should be provided as an appendix: student completes all sections of the template and attempts interpretation, demonstrating basic understanding of hypothesis testing, descriptive statistics, data visualisation, and has applied and interpreted an appropriate statistical test to reach a conclusion. R code appendix includes code provided during module, but includes no attempt to edit or extend code beyond the basic template.

(Grade C; mark range 50-59%)

Good – A good student should have a good knowledge of how to read an existing dataset into R, calculate descriptive statistics, and produce good data visualisations, exploring options to change settings in provided code, apply basic statistical tests appropriately, and appropriately interpret the results to draw sound conclusions.

Assessment 1: complete a pre-prepared template for a quantitative analysis write-up using only descriptive statistics and data visualisation: student completes all sections of the template, demonstrating ability to edit some aspects of the provided template code, and interprets appropriately.

Assessment 2: Mini-paper on own research question and data or pre-prepared question and provided dataset in R (specified format: very short introduction, data collection and analytical methods fully explained, detailed results section including data visualisation in R, conclusions). All R code used should be provided as an appendix: student completes all sections of the template and attempts interpretation, demonstrating good understanding of hypothesis testing, descriptive statistics, data visualisation, and has applied and interpreted an appropriate statistical test to reach an appropriate conclusion. R code appendix includes code provided during module, with appropriate edits or additions beyond the basic template.

(Grade B; mark range 60-69%)

Excellent - An excellent student should have excellent knowledge of how to read an existing dataset into R, calculate descriptive statistics, and produce excellent data visualisations, exploring options to change settings in provided code, apply basic statistical tests appropriately, and appropriately interpret the results to draw sound conclusions.

Assessment 1: complete a pre-prepared template for a quantitative analysis write-up using only descriptive statistics and data visualisation: student completes all sections of the template, demonstrating ability to edit multiple aspects of the provided template code, and interprets accurately.

Assessment 2: Mini-paper on own research question and data or pre-prepared question and provided dataset in R (specified format: very short introduction, data collection and analytical methods fully explained, detailed results section including data visualisation in R, conclusions). All R code used should be provided as an appendix: student completes all sections of the template and interprets accurately, demonstrating excellent understanding of hypothesis testing, descriptive statistics, data visualisation, and has applied and interpreted an appropriate statistical test to reach an appropriate conclusion. R code appendix includes code provided during module, with multiple appropriate edits or additions beyond the basic template that improve interpretation or communication of results.

(Grade A; mark range 70-100%)

Learning Outcomes

• Manipulate and analyse data to calculate descriptive statistics and produce informative data visualisations using Microsoft Excel, R, RStudio and appropriate R packages.

• apply appropriate statistical tests to datasets and draw conclusions from them

• explain why and how quantitative data analysis methods are used to answer questions in conservation and natural resource management, and demonstrate understanding of why samples are taken from populations and how to design a testable hypothesis