Statistics for Health Data Science

IIDS67631 Statistics for Health Data Science 15 Semester 1 Postgraduate Taught Level 7 Hui Guo Unit coordinator Division of Informatics, Imaging and Data Sciences 1 FHEQ level (Framework for Higher Education Qualifications) ' Masters/Integrated Masters P4 ' European Credit Transfer & Accumulation System Rating : 7.5 Currently, there is a large amount of health and related data that is not analysed in order to provide insights into healthcare delivery.  A core skill required of a health data scientist is to be able to analyse various forms of health data; the unit will cover the fundamental knowledge required to do this including understanding data; pre-processing steps; key analytical skills and a suitable statistical programming language.  The unit will introduce students into what can be achieved through the analysis of health data.  Key research questions will be drawn from teaching staff and their networks to illustrate these techniques. Currently, there is a large amount of health and related data that is not analysed in order to provide insights into healthcare delivery.  A core skill required of a health data scientist is to be able to analyse various forms of health data; the unit will cover the fundamental knowledge required to do this including understanding data; pre-processing steps; key analytical skills and a suitable statistical programming language.  The unit will introduce students into what can be achieved through the analysis of health data.  Key research questions will be drawn from teaching staff and their networks to illustrate these techniques. To introduce the student to a range of mathematical and statistical techniques that are widely used when analysing health data, and to demonstrate what can be acheived when using health data. The focus is on explaining which techniques are available and how best to use them, rather than going into details of how a method works (it is more useful to know how a method could be implemented and when to use rather than understand theoretical principles). On completion the student should be aware of a range of techniques and have experience of writing scripts and executing them in R. Indicative content: <ul> <li> Overview of key statistical measures and theory</li> <li> Introductory mathematical toolkit - Probability theory</li> <li> Data pre-processing - Cleaning, visualisation and integrity checks</li> <li> Supervised learining - Goodness of fit, Rik/loss funcations (correlation, RMSE, accuracy, sensitivity, specificity); Univariable methods and distributions; Normal, Poisson, Bionomial, Multinomial, Gamma-families; Chi-squared test, t-test, Wilcoxon, ANOVA, Kruskal-Wallis</li> <li> Classification and Regression - Linear models; Generalised linear models</li> <li> Data mining/unsupervised learning - Principle Component Analysis; Hierarchical clustering; Partitional clustering</li> <li> Study designs - Trial-type design; Cohort (observational) studies; Confounding and causality.</li> </ul> <ul> <li> Identify and describe the steps required to analyse a set of health data</li> <li> Describe and explain key ideas and concepts in statistics</li> <li> Know how to prepare data sets for analysis</li> <li> Appreciate the key concepts in study design</li> <li> Understand the ideas behind building mathematical models</li> </ul> <ul> <li> Represent problems mathematically, in a way in which allows statistical scripts to be written to solve them</li> <li> Identify and apply approriate mathematical and statistical methods to analyse/model a given health data set</li> </ul> <ul> <li> Execute and write statistical scripts to compute basic statistical measures and analyse data</li> <li> Prepare a data sete for analysis</li> </ul> <ul> <li> Demonstrate statisical programming skills</li> <li> Demonstrate experience of solving applied problems</li> <li> Communicate analyses and interpretation of results of health data</li> </ul> Analytical skills Demonstrate statistical programming skills Problem solving Demonstrate experience of solving problems The course will be taught in a blended-learning format: basic knowledge and directed reading will be provided via eLearning so as to introduce students with key knowledge.  The face-to-face time will consist of a series of lectures and discussions in which core concepts (introduced through pre-reading) will be re-capped and any further development discussed, as well as supervised computer time during which practical software and programming problems will be explored.  When possible, lectures will be recorded and distributed online.  The F2F lectures will be delivered throughout Semester 1, each week focusing on different analysis methods. The unit assessment will require the student to write scripts to demonstrate their understanding and application of the techniques covered in the unit and a written report describing the justification of method; key findings and working.  There will be online tutor support for the eLearning preparation and tutorials will be made available for students with academic staff to ensure that students are continuing to progress through the unit. 0 Other 20% 3 Report 80% Summative assignments include one long report at 1500 words counting for 80%, and one short report at 750 words counting for 20%.Each assignment should include statistical scripts demonstrating the analysis of data and a written report (in paper style) to justify methods and explanation of work.Formative assignments will be delivered through a wide range of interactive exercises and supervised practical exercises.  Feedback on summative assignments will be delivered via Blackboard within 15 working days with drop-in sessions held for further feedback discussions. Verbal feedback will be delivered real-time.  MSc Health Data Science PT MSc Health Data Science PGDT Taught Component Mandatory PG Dip Health Data Science PT PG Diploma Health Data Science PGDT Taught Component Mandatory Health Data Science - CPD Health Data Science - CPD PGDT Taught Component Optional MSc Health Data Science FT MSc Health Data Science FT PGDT Taught Component Mandatory PG Dip Health Data Science FT PG Dip Health Data Science FT PGDT Taught Component Mandatory N Lectures 18 Practical classes & workshops 24 Tutorials 2 0 106