Skip to main content

Unit information: Quantitative and Computational Methods in 2020/21

Unit name Quantitative and Computational Methods
Unit code BIOL20020
Credit points 20
Level of study I/5
Teaching block(s) Teaching Block 1 (weeks 1 - 12)
Unit director Dr. Christos Ioannou
Open unit status Not open
Pre-requisites

None.

Co-requisites

None.

School/department School of Biological Sciences
Faculty Faculty of Life Sciences

Description

Being able to process and analyse data are now key skills across biological research, from genes to ecosystems. The aim of this unit is to teach these skills, and to enable students to teach themselves more advanced data analysis skills in the future.

The unit will give students an understanding of how to design data collection and experiments. How to then analyse this data is the major component of this unit, from the basic principles of statistical analysis to how these analyses are applied to real-world biological data sets, including how to ensure the assumptions of these analyses are met. Students will gain an understanding of, and extensive hands-on practice with, linear modelling to analyse different types of problems, and be shown how these correspond to older methods such as linear regression, t-tests and ANOVA, each of which have more restricted use.

The unit will use the programming language R which is widespread and now the most common data-analysis program for biological research. A gradual introduction to the language over successive practical classes will give students supervised hands-on experience with the program and how to use it to import and process, visualise, and analyse data.

Across the unit, students will gain training in basic computer coding which is likely to be of use in their projects in years 3 and 4, and beyond into the wider world. In the second half of the unit, the concept and application of loops will be introduced, enabling students to write their own randomisation tests, and as a window into more computationally intense data analysis methods used in biology to deal with ‘big data’. As an example of such methods, social network analysis will be introduced and students will be able to use this approach in their summative report.

Intended learning outcomes

1) Understand the principles of designing experiments and data collection and how they underpin good statistical analysis (and hence good science).

2) Understand the principles of linear modelling and non-parametric tests, and be able to apply these to real-world biological data sets, including being able to explain and evaluate the assumptions and limitations of the tests.

3) Understand why and when using a programming language, particularly R, is favourable to other approaches of data analysis, especially in relation to big data.

4) Understand the basics of computer programming, specifically using base R to run statistical tests, manipulate data and create simple plots.

Teaching details

1-hour weekly lectures (10 hours in total) to give the biological context and theory for the set statistical exercises. These will be in the format of pre-recorded videos that students can view in their own time. Students will attend one of two 2-hour synchronous drop-in help sessions per week for supporting the statistical exercises (20 hours in total per student), one scheduled early in the day and the other scheduled later (UK time); students attend one of these chosen to suit their time zone.

Assessment Details

Attendance at practical sessions is mandatory.

Summative: Practical report (40%) and multiple-choice January exam

(60%). The multiple-choice exam may be online and will start at the same time for all students, with the order of questions being random.

Formative: Practice multiple choice test with feedback

Reading and References

There is no single text that covers the content covered in this unit. There are, however, a multitude of websites and free online books that will be able to help students in different aspects of the unit.

Feedback