MA317-7-AU-CO:
Modelling Experimental Data

The details
2019/20
Mathematical Sciences
Colchester Campus
Autumn
Postgraduate: Level 7
Current
Thursday 03 October 2019
Saturday 14 December 2019
15
01 October 2019

 

Requisites for this module
(none)
(none)
(none)
(none)

 

MA321

Key module for

MSC G10124 Mathematics,
MSC G30412 Data Science,
MSC G30424 Data Science,
MSC G304PP Data Science with Professional Placement,
DIP G30009 Statistics,
MSC G30012 Statistics

Module description

This module is concerned with the application of linear models to the analysis of data. The underlying assumptions are discussed and general results are obtained using matrices. The standard approach to the analysis of normally distributed data using ANOVA is introduced. Methods for the design and analysis of efficient experiments are introduced. The general methodology is extended to logistic regression and the analysis of multidimensional contingency tables.

Module aims

Syllabus

Simple linear regression
1 Link between maximum likelihood and least Squares. OLS for linear regression.
2 Pythagoras and the ANOVA table. The estimation of $rc2 .
3 Confidence intervals for parameters and prediction intervals for future observations
General results using matrices
4 Matrix formulation. Normal equations. Solution. Moments of estimators.
5 Gauss-Markov theorem. Estimability
6 H, Q, V.
7 Generalised and weighted least squares.
Multiple regression
8 Multiple regression. Subdividing the regression sum of squares. Lack of fit and pure error.
9 Regression diagnostics. Leverage, Residual plots. Multicollinearity, Serial correlation
10 Model selection. Stepwise methods. Cp plots.
11 Curvilinear regression. Orthogonal polynomials.
12 ANCOVA
Designed experiments
13 Completely randomised experiment. Replication. ANOVA. Contrasts.
14 Randomized blocks. Latin squares. Multiple comparison tests.
15 ANOVA with random effects
16 Balanced incomplete blocks. ANOVA (relation to bivariate regression)
17 Factorial experiments: notation. ANOVA. Model selection.
18 Factorials and blocks: confounding and partial confounding.
19 Fractional replicates. Aliases.
Non-linear models
20 The Newton-Raphson procedure. Application to growth curves.
21 Estimation, confidence intervals, tests.
Logit and loglinear models
22 Logistic regression
23 Loglinear models. Birch’s result. Hierarchy principle. Iterative proportional fitting.
24 Independence. Conditional independence. Multistage analysis.
25 Simpson’s paradox. Incomplete tables. Square tables.

Module learning outcomes

On completion of the module students should be able to:
- calculate confidence intervals for parameters and prediction intervals for future observations;
- understand how to represent a linear model in matrix form;
- check model assumptions and identify influential observations;
- identify simple designed experiments;
- construct factorial experiments in blocks;
- adapt linear models to fit growth curves;
- carry out logistic regression;
- analyze cross-tabulated data using log linear models;
- analyse linear models using R.

Module information

No additional information available.

Learning and teaching methods

The module has 33 contact hours in total. These consist of 25 lectures, 4 labs and 4 classes during the autumn term, together with 3 revision lectures in the summer term.

Bibliography

  • Faraway, Julian James. (©2015) Linear models with R, Boca Raton, FL: CRC Press. vol. Chapman & Hall/CRC texts in statistical science series

The above list is indicative of the essential reading for the course. The library makes provision for all reading list items, with digital provision where possible, and these resources are shared between students. Further reading can be obtained from this module's reading list.

Assessment items, weightings and deadlines

Coursework / exam Description Deadline Weighting
Coursework Initial Task 06/11/2019 25%
Coursework Group Project and Group Presentation 11/12/2019 75%
Exam 180 minutes during Summer (Main Period) (Main)

Overall assessment

Coursework Exam
20% 80%

Reassessment

Coursework Exam
0% 100%
Module supervisor and teaching staff
Prodessor Berthold Lausen (blausen@essex.ac.uk), Dr Stella Hadjianto (sh19670@essex.ac.uk), Dr Joe Bailey (jbaileyf@essex.ac.uk)
Professor Berthold Lausen (blausen@essex.ac.uk)

 

Availability
Yes
Yes
No

External examiner

Prof Fionn Murtagh
Professor of Data Science
Resources
Available via Moodle
Of 40 hours, 38 (95%) hours available to students:
2 hours not recorded due to service coverage or fault;
0 hours not recorded due to opt-out by lecturer(s).

 

Further information
Mathematical Sciences

Disclaimer: The University makes every effort to ensure that this information on its Module Directory is accurate and up-to-date. Exceptionally it can be necessary to make changes, for example to programmes, modules, facilities or fees. Examples of such reasons might include a change of law or regulatory requirements, industrial action, lack of demand, departure of key personnel, change in government policy, or withdrawal/reduction of funding. Changes to modules may for example consist of variations to the content and method of delivery or assessment of modules and other services, to discontinue modules and other services and to merge or combine modules. The University will endeavour to keep such changes to a minimum, and will also keep students informed appropriately by updating our programme specifications and module directory.

The full Procedures, Rules and Regulations of the University governing how it operates are set out in the Charter, Statutes and Ordinances and in the University Regulations, Policy and Procedures.