Module and Programme Catalogue

Search site

Find information on

2019/20 Taught Postgraduate Module Catalogue

EPIB5042M Modelling Prediction and Causality with Observational Data

15 creditsClass Size: 30

Module manager: Professor Mark S Gilthorpe
Email: m.s.gilthorpe@leeds.ac.uk

Taught: Semester 1 View Timetable

Year running 2019/20

Pre-requisite qualifications

Academic entry requirements

A 1st degree in a quantitative or scientific subject area with substantial mathematical, statistical or numeracy components (at least 2:1). We also consider working experience (two years or more) of research in a quantitative subject area. Non-graduates who: have successfully completed three years of a UK medical degree; are normally ranked in the top 50% of the year 3 cohort; and wish to take the Health Data Analytics MSc as an intercalated programme, will also be accepted.

English language requirements

An overall score of 7.0 on IELTS (International English Language Testing System) with at least 6.0 in writing and no other skill below 6.5; from a TOEFL paper-based test the requirement is a minimum score of 600, with 4.5 in the Test of Written English (TWE); from a TOEFL computer-based test the requirement is a minimum score of 250, with 4.5 TWE; from a TOEFL Internet-based test the requirement is a minimum score of 100, with 25 in the "Writing Skills" score.

This module is mutually exclusive with

EPIB5023MIntroduction to Modelling

Module replaces

EPIB5023M Introduction to Modelling

This module is not approved as an Elective

Module summary

The module is designed to give students a comprehensive introduction to linear modelling and equip them with the skills and knowledge necessary to analyse various outcome data types. By the end of the module students will be able to identify suitable linear models for analysing a variety for different outcome types; fit a linear model using statistical software including selection of model parameters; compare between models and assess the appropriateness or otherwise of the fitted model.

Objectives

- To provide a comprehensive understanding of the principles (model theory, limitations, assumptions) underpinning the use of (generalised) linear modelling of observational data;
- To enable students to apply their knowledge to a range of situations and datasets such that they can fit a variety of linear models and compare model fit between them;
- To understand the difference between predictive modelling and causal inference modelling;
- To understand linear modelling techniques for predictive modelling;
- To understand linear modelling techniques for causal inference modelling;
- To critically appraise the use of linear models within the literature.

Learning outcomes
By the end of this module the student should be able to:

- Describe the principles of linear modelling including a knowledge of which type of model is appropriate for different outcome data types;
- Explain the principles of the method of least squares and maximum likelihood for estimating parameters in a linear model;
- Formulate linear models in the statistical software R;
- Compare and contrast different models, such as prediction model and causal inference models;
- Be familiar with Directed Acyclic Graphs (DAGs) for selecting model covariates in causal inference models;
- Explain the principle of parsimony;
- Apply a variety of diagnostic and validity checks of model fits;
- Critically appraise the use of linear models for observational research.

Skills outcomes
Statistical analysis skills. Practical modelling skills for observational data and critical evaluation of the use of linear models.


Syllabus

- Introduction to linear models;
- Introduction to statistical software R for fitting linear models;
- Correlation and simple linear regression;
- Multiple linear regression, including maximum likelihood estimation;
- Model fitting, parameter estimation and interpretation;
- Model diagnostics;
- Generalised linear modelling including logistic regression analysis and Poisson regression;
- Introduction to DAGs.

Teaching methods

Delivery typeNumberLength hoursStudent hours
Class tests, exams and assessment11.501.50
Lecture111.0011.00
Practical221.5033.00
Private study hours104.50
Total Contact hours45.50
Total hours (100hr per 10 credits)150.00

Private study

At least 4 hours per week of private study of additional course materials to support lectures and tutorial work. In addition, students are expected to spend 34 hours on each of the two assignments.

Opportunities for Formative Feedback

The weekly practical sessions will form the basis of continuous student monitoring. In addition, the two assignments which are staggered during the course will allow the module leader to monitor student progress and assess whether there are students in need of additional help, or whether there are particular topics that require further elucidation.

Methods of assessment


Coursework
Assessment typeNotes% of formal assessment
ReportProject report - 1000 words33.30
ReportProject report - 1000 words33.30
Total percentage (Assessment Coursework)66.60

There is no compensation across the two items of coursework. Students need to pass both components.


Exams
Exam typeExam duration% of formal assessment
Unseen exam 2 hr 00 mins33.40
Total percentage (Assessment Exams)33.40

Normally resits will be assessed by the same methodology as the first attempt, unless otherwise stated

Reading list

The reading list is available from the Library website

Last updated: 30/04/2019

Disclaimer

Browse Other Catalogues

Errors, omissions, failed links etc should be notified to the Catalogue Team.PROD

© Copyright Leeds 2019