Computer Science (Human Computer Interaction) (3 Years) [BSc]

Modelling Social Inequality

Unit code: SOST30031
Credit Rating: 20
Unit level: Level 3
Teaching period(s): Semester 1
Offered by Social Statistics
Available as a free choice unit?: Y




The unit aims to:

(i). Outline some important studies, measures, concepts and theories of social inequality, both in the UK and worldwide.
(ii) Introduce some valuable web-based resources of secondary quantitative data, both for the UK and worldwide.
(iii) Explain how linear regression may be used to test hypotheses regarding social inequalities when the response variable has an interval scale, and how logistic regression may be used when the response variable has two categories.
(iv) Demonstrate how the SPSS statistical package may be used to carry out such analyses.
(v) Give details of assessing the statistical quality of linear and logistic regression model fit, and the substantive interpretation of the results.
(vi) Provide examples of the use of linear and logistic regression in the literature on social inequality.


Based on the central theme of investigating social inequality, I introduce the concepts, theory and application of two important statistical modelling techniques in social science: multiple regression and logistic regression.

==============Lecture Schedule (10 x 2hr lectures)

1. Some important studies, measures and concepts of social inequality.
2. Identifying secondary data on social inequality (e.g. via; units of analysis; area and individual level data; types of response and explanatory variable.
3. Introducing linear regression - modelling an interval response variable like income. software.
4. linear regression continued. Model selection.
5. linear regression continued. Checking the assumptions, reporting the results.
6. Examples of linear regression in studies of social inequality in the literature such as measuring social distance.
7. Introducing logistic regression - modelling a dichotomous response variable like unemployment.
8. Logistic regression continued - odds ratios, model selection.
9. Group student presentations of examples of inequality 
10. Review and exam preparation

Teaching and learning methods

The module will involve: lectures, computer labs, and data analysis tasks using SPSS.

Extensive use will be made of relevant on-line resources including: literature resources and examples of use of software. Moreover, the data itself will be accessed on-line. 

Blackboard resources will be used to provide lecture materials.

Learning outcomes

Student should/will be able to

Knowledge and Understanding:  A critical understanding of when linear or logistic regression analysis might be appropriate to analyse quantitative social data given substantive hypotheses on social inequality. Some social outcomes or indices like income are on interval scales for which linear regression may be used. Other social outcomes like education or employment have two categories (or can be re-coded to have two categories) for which logistic regression may be used.

Intellectual skills:  How to formulate hypotheses to investigate social inequality with linear and regression models. How to decide which variables to include on a substantive basis.

Practical skills:  How to fit linear regression models in SPSS.

Transferable skills and personal qualities: Ability to formulate and run linear and logistic regression models for other substantive problems. Ability to use SPSS.

Assessment Further Information

This course will be assessed by 1 x 2,000 word written assignment (40%) and 1 x 2 hour exam (60%).

Recommended reading


Wilkinson R. Pickett K 'The Spirit Level: Why Equality is Better for Everyone'.

Jones O. (2012) 'Chavs: The Demonization of the Working Class' ; 2nd Revised edition. Verso Books

Dorling D. (2011) 'Injustice: Why Social Inequality Persists' (Paperback). Policy Press.

Dorling D (2013) 'The 32 Stops'. Penguin.

Field A (2013) Discovering Statistics using IBM SPSS Statistics [Paperback]. Sage.

On-line Resources

Is Britain Pulling Apart?
Economic & Social Data Service (ESDS)
ESDS international
Research Methods Centre

Feedback methods


All Social Statistics courses include both formative feedback – which lets you know how you’re getting on and what you could do to improve – and summative feedback – which gives you a mark for your assessed work.

Study hours

  • Lectures - 20 hours
  • Practical classes & workshops - 10 hours
  • Independent study hours - 170 hours

Teaching staff

Nicholas Shryane - Unit coordinator

▲ Up to the top