Module Specification |
The information contained in this module specification was correct at the time of publication but may be subject to change, either during the session because of unforeseen circumstances, or following review of the module at the end of the session. Queries about the module should be directed to the member of staff with responsibility for the module. |
Title | ADVANCED STATISTICS FOR BIOLOGICAL RESEARCH | ||
Code | LIFE707 | ||
Coordinator |
Prof AM Mortimer Functional and Comparative Genomics A.M.Mortimer@liverpool.ac.uk |
||
Year | CATS Level | Semester | CATS Value |
Session 2016-17 | Level 7 FHEQ | Continuing Education Session | 15 |
Pre-requisites before taking this module (other modules and/or general educational/academic requirements): |
SEEBELOW Entry into the MBiolSci, MRes (ASCR, PGSC) or MSc (ASCT) programmes Students must also have successfully completed a Level 5 or Level 6 undergraduate statistics course (e.g. University of Liverpool BIOL215) or equivalent. |
Modules for which this module is a pre-requisite: |
Co-requisite modules: |
Linked Modules: |
Teaching Schedule |
Lectures | Seminars | Tutorials | Lab Practicals | Fieldwork Placement | Other | TOTAL | |
Study Hours |
2 For each of the 9 topics covered in the module, there is an electure provided on Vital. This gives guidance on the recommended topic reading, the underlying theory and practical examples of the statistical topic in question. 1 This lecture introduces the module to the student cohort |
18 2hr workshops in computer centres are held each week to accompany each electure. These provide one to one teaching and feedback from academic staff. |
21 | ||||
Timetable (if known) |
Introduction to directed self-learning in advanced statistics and the learning environment. Registration for this module requires you have to previously and successfully completed an undergraduate
|
Students should attempt to complete the activities highlighted in each electure before coming to the workshop. Difficulties in understanding can then be discussed in the workshop.
|
|||||
Private Study | 129 | ||||||
TOTAL HOURS | 150 |
Assessment |
||||||
EXAM | Duration | Timing (Semester) |
% of final mark |
Resit/resubmission opportunity |
Penalty for late submission |
Notes |
Open Book Written Exam | 2 hr | Week 11, semester 1 | 50 | Yes | Standard UoL penalty applies | Examination of concepts, data analysis and interpretation Notes (applying to all assessments) Assessment 1: On-line MCQ assessment : Students will have 3 h to complete this MCQ assessment through VITAL. For 607 students the time for this assessment will be agreed with the student and will depend on the time zone of the country in which the student is working. Assessment 2: Independent analysis of datasets and report writing. Students will have 3 days to complete this assessment and it will submitted through VITAL. Assessment 3: will be conducted in the final week of the module and is time limited. It will involve understanding of concepts and data analysis/ interpretation. It will be conducted under examination conditions, and for students working off campus, appropriate invigilation will be arranged by the supervisor of the group in which the student is undertaking his/her placement. The time of this assessment will be agreed with the student and will depend on the time zone of the country in which the student is working. |
CONTINUOUS | Duration | Timing (Semester) |
% of final mark |
Resit/resubmission opportunity |
Penalty for late submission |
Notes |
Coursework | 3h | Week 3 Semester 1 | 25 | No reassessment opportunity | Standard UoL penalty applies | The understanding of basic statistical principles is covered in this assessment. There is no reassessment opportunity, This is an in-course MCQ evaluating baseline understanding |
Coursework | 6 hr | In week 7 semester 1 over a 3 | 25 | No reassessment opportunity | Standard UoL penalty applies | In-course open-book independent data analysis There is no reassessment opportunity, |
Aims |
|
The aim of this module is to enable students to analyse biological data by 1. Choice of appropriate statistical approaches to test hypotheses; 2. Critical understanding of the use of a range of advanced statistical tests for appropriate analysis and model fitting of a range of bi ological datasets; 3. Using the software package, R. 4. Synthesizing information, summarising statistical findings and using hypothesis testing to critically review evidence from experimental data to support conclusions. |
Learning Outcomes |
|
Use appropriate statistical approaches to test hypotheses. |
|
Critically evaluate a range of advanced statistical tests for appropriate analysis and modelling of a range of biological datasets. |
|
Use the software package, R, for these statistical tests and modelling of data | |
Synthesise information from data analysis, test statistical hypotheses and critically review evidence to support conclusions. |
Teaching and Learning Strategies |
|
Lecture - This lecture introduces the module to the student cohort Introduction to directed self-learning in advanced statistics and the learning environment. Registration for this module requires you have to previously and successfully completed an undergraduate statistics module at Liverpool or elsewhere. |
|
Electure - For each of the 9 topics covered in the module, there is an electure provided on Vital. This gives guidance on the recommended topic reading, the underlying theory and practical examples of the statistical topic in question. |
|
Practical - 2hr workshops in computer centres are held each week to accompany each electure. These provide one to one teaching and feedback from academic staff. Students should attempt to complete the activities highlighted in each electure before coming to the workshop. Difficulties in understanding can then be discussed in the workshop. |
Syllabus |
|
1 |
1 Each topic will follow a similar format, consisting of four main sections: a. Introduction to the particular topic and relevant theory b. Topic-specific examples and explanations of typical statistical output c. Step-by-step instructions on the use of R d. Practice in analysis of data and reporting of results Topic 1 Introduction to how the module runs, the teaching and learning environment, a review of statistical inference tests and how to set up R and read in data. By the end of this topic you will be clear about how to approach your learning, the learning timetable and framework, refreshed your basic statistical knowledge regarding elementary types of statistical test and statistical inference, and grasped the essentials of the R environment. Topic 2 The R environment for elementary statistical tests. This topic provides examples of simple statistical tests (eg. chi-square, t-tests) and data exploration approaches (box plots, normality testing). Topic 3 Introduction to the concept of general linear models (GLMs). In this topic we consider the philosophical and practical approach to data analysis through general linear modelling and illustrate it through linear regression. The latter are techniques that should be reasonably familiar to you and we revise how to test for significance, to test the assumptions underlying the analyses and how to draw the correct conclusions. Topic 4 GLMs and Analysis of variance. The analysis of designed experiments is a mainstay in all biological research. Assessing the relationship between treatment factors that may or may not significantly influence the response variable depends on the design of the experiment and how you replicated measurements. In this topic we look at how to use GLMs for such experiments. Topic 5 Extending the linear model. Generalized linear modelling (GLM) is an important core concept in statistics. In this topic you will learn how to further analyse data by multiple regression where error distributions are both normally distributed and where they are not. Topic 6 Model selection. Here we go into greater depth illustrating how you choose and assess what is the ''best'' model to statistically describe a set of data. < strong>Topic 7 Non-linear relationships. In this topic we consider issues surrounding the statistics of what is colloquially known as ''curve fitting'' where the response variable is continuous. In particular, we consider the rectangular hyperbola from the perspective of enzyme kinetics. Topic 8 Probits, logits, logistic regression and dose response analysis. Picking up on topics 5, 6 and 7 here we look further at the application of GLMs to analysing survivorship, proportional data and what are commonly known as dose response curves. Topic 9 Genomic analysis. R is particularly powerful for analysing large data sets. In this final topic we explore approaches used to analyse genomic data (micro-array, RNA-seq) in genomics studies. Topic 10 Assessment 3. This is the final assessment for this module, which occurs under formal examination conditions. |
Recommended Texts |
|
Reading lists are managed at readinglists.liverpool.ac.uk. Click here to access the reading lists for this module. Explanation of Reading List: |