UNIVERSITY OF KENT
Confirmation that this version of the module specification has been approved by the School
Learning and Teaching Committee:
……2nd April 2015…………………………….(date)
SECTION 1: MODULE SPECIFICATION
1.
Title of the module
Regression Models (MA632and MA612)
2.
School or partner institution which will be responsible for management of the module:
School of Mathematics, Statistics and Actuarial Science
3.
Start date of the module
Before 2006 (revised version start date September 2015)
4.
The number of students expected to take the module
125
5.
Modules to be withdrawn on the introduction of this proposed module and consultation with other
relevant Schools and Faculties regarding the withdrawal
None, revision of an existing module
6.
The level of the module (e.g. Certificate [C], Intermediate [I], Honours [H] or Postgraduate [M])
MA632 – I-level ; MA612 – H-level
7.
The number of credits and the ECTS value which the module represents: 15 (ECTS 7.5)
8.
Which term(s) the module is to be taught in (or other teaching pattern): Spring term
9.
Prerequisite and co-requisite modules
For the I-level module
Prerequisite modules: MA321 (Calculus and Mathematical Modelling); MA322 (Proofs and numbers);
MA323 (Matrices and Probability) or MA312 (Introduction to Financial Concepts); and MA306
(Statistics).
There are no co-requisite modules.
There are no prerequisite modules for the H-level module, though students are expected to have
studied material equivalent to that covered in the modules listed above. There are no co-requisite
modules.
10. The programmes of study to which the module contributes
For the I-level module: BSc (Hons) Mathematics, BSc (Hons) Mathematics & Statistics, BA (Hons)
Mathematics and Accounting & Finance, BSc (Hons) Financial Mathematics (including programmes
with a year in industry), BSc (Hons) Mathematics with Secondary Education, BSc (Hons)
Mathematics with a Foundation Year, MMath Mathematics, MMathStat Mathematics and Statistics
1
UNIVERSITY OF KENT
For the H-level module: Graduate Diploma in Statistics, International MSc in Statistics, International
MSc in Statistics with Finance.
11. The intended subject specific learning outcomes
On successful completion of this module, I-level students will be able to demonstrate:
(a) a reasonable ability to derive, from first principles and using matrix algebra, theoretical results
relating to fitting regression models by least squares;
(b) a reasonable ability to fit regression models to data, and carry out related statistical inferences,
using both hand calculation and appropriate computer software;
(c) a reasonable ability to use residual plots and other techniques to check the assumptions
underlying regression analysis;
(d) a reasonable ability to identify outlying and influential observations;
(e) a reasonable ability to choose between alternative models for sets of data.
On successful completion of this module, H-level students will also be able to demonstrate:
(f) a systematic understanding of the areas of simple linear and multiple regression modelling.
(g) an ability to explore the statistical literature to extend their knowledge of regression modelling to
include logistic regression models.
12. The intended generic learning outcomes
The module provides an introduction to the theory and practice of regression. Students should
emerge with an appreciation of the power of this technique, and with the ability to use it in the
analysis of data.
On successful completion of the Module, I-level students will have:
(a) developed their understanding of probability and statistics;
(b) applied a range of mathematical techniques to solve statistical problems;
(c) developed their ability to abstract the essentials of problems and to formulate them
independently;
(d) improved their key skills in written communication, numeracy and problem solving;
(e) developed their ability to use statistical software;
(f) enhanced their study skills and ability to work with relatively little supervision.
On successful completion of the Module, H-level students will also have:
(g) demonstrated an ability to extend their existing knowledge of statistics into new areas through
independent study.
13. A synopsis of the curriculum
Definition of the linear model and regression.
Simple linear regression: least squares estimates; expectations, properties of estimators. Standard
errors and confidence intervals for parameters. Sums of squares, the ANOVA table. Prediction
intervals.
Regression with two explanatory variables.
Matrix formulation of the model, multiple regression, extra sum of squares principle. Residuals:
properties, use in checking model assumptions.
Model selection strategies.
Link between ANOVA and regression through dummy variables. One way Analysis of Variance.
In addition, for H-level students:
Logistic regression – the logit transformation, fitting a linear logistic model, interpretation of fitted
model, analysis of deviance, overdispersion.
14. Indicative Reading List
Draper,N.R. and Smith, H. (1998) Applied Regression Analysis. 3rd edition, New York, Wiley.
[Recommended]
2
UNIVERSITY OF KENT
Chatterjee, S and Hadi, A.S. (2012) Regression Analysis by Example. 5th edition, Hoboken, New
Jersey, Wiley. [Background]
Freedman, D.A. (2005) Statistical Models: Theory and Practice, Cambridge University Press.
[Background]
Collett, D. (2003) Modelling Binary Data. 2nd edition. Boca Raton, Chapman & Hall/CRC.
[Recommended for H-level students]
Dobson, A.J. and Barnett, A. G. (2008) An Introduction to Generalized Linear Models. 3rd edition.
Boca Raton, Chapman & Hall/CRC. [Recommended for H-level students]
15. Learning and Teaching Methods, including the nature and number of contact hours and the total
study hours which will be expected of students, and how these relate to achievement of the intended
module learning outcomes
Number of contact hours: For I-level students, 41, including 36 lectures and 5 hours of computing
workshops. In addition, for H-level students, 2 hours related to the directed reading task.
Number of independent learning hours: For I-level students,109. For H-level students, 107.
Total study hours: 150
For all students, the lectures contain numerous worked examples to illustrate the theory and show
how it is applied to practical problems.
Some exercises are provided as separate sheets and others are interspersed in the lecture notes.
These are intended to reinforce the material that is covered in the lectures, to encourage the student
to study the lecture notes and to make linkages between the lectures and the computer workshops.
Solutions to all exercise sheets are made available to students after they have attempted them.
The computing workshops introduce the students to the basic software commands and then
encourage them to explore the software in more depth by addressing a series of questions. Support
is available during the classes.
Some of the lecture hours are devoted to discussion of exercises and coursework.
Subject specific learning outcome 11(a) and generic learning outcomes 12(a),(c) are addressed by
lectures. Outcomes 11(b)-(e) are addressed by a combination of lectures and computing workshops.
For I-level students, generic learning outcomes 12(b),(d)-(f) will be addressed by computing
workshops and though the assessed coursework.
For H-level students, subject specific learning outcome 11(f) and generic learning outcomes
12(b),(d)-(f) will be addressed by computing workshops and the formative exercises. Directed
reading with staff support is used to address learning outcomes 11(g) and 12(g).
16. Assessment methods and how these relate to testing achievement of the intended module learning
outcomes
The module will be assessed by examination (90%) and coursework (10%).
Coursework: I-level students carry out practical regression analyses in two equally-weighted
assessments. Only limited help will be provided with these assessments. The coursework
will assess learning outcomes 11(b)-(e) and 12(a)-(f). H-level students will complete
formative exercises and these practicals (formative only) and will also complete an
assignment related to the directed reading task, This will assess learning outcomes 11(g)
and 12(g).
Examination: This will be a 2-hour written examination in the Summer Term that consists of
multipart questions requiring a mix of short and long answers that test to varying levels of
proficiency learning outcomes 11(a)-(e) and 12(a)-(c). In addition, for H-level students, their
examination will also assess learning outcome 11(f).
3
UNIVERSITY OF KENT
17. Implications for learning resources, including staff, library, IT and space
None – this is an existing module.
18. The School recognises and has embedded the expectations of current disability equality legislation,
and supports students with a declared disability or special educational need in its teaching. Within
this module we will make reasonable adjustments wherever necessary, including additional or
substitute materials, teaching modes or assessment methods for students who have declared and
discussed their learning support needs. Arrangements for students with declared disabilities will be
made on an individual basis, in consultation with the University’s disability/dyslexia support service,
and specialist support will be provided where needed.
19. Campus where module will be delivered:
Canterbury
4