University of Surrey - Guildford
Registry
  
 

  
 
Registry > Provisional Module Catalogue - UNDER CONSTRUCTION & SUBJECT TO CHANGE
View Module List by A.O.U. and Level  Alphabetical Module Code List  Alphabetical Module Title List  Alphabetical Old Short Name List  View Menu 
2011/2 Provisional Module Catalogue - UNDER CONSTRUCTION & SUBJECT TO CHANGE
 Module Code: SOCM018 Module Title: STATISTICAL MODELLING
Module Provider: Sociology Short Name: SOCM04
Level: M Module Co-ordinator: PICHLER F Dr (Sociology)
Number of credits: 15 Number of ECTS credits: 7.5
 
Module Availability

Sring Semester
Assessment Pattern

Two exercises which will require the students to interrogate a multivariate dataset, select and fit appropriate statistical models (using SPSS) and interpret the results.
Module Overview
Prerequisites/Co-requisites
Module Aims

The aim of this module is to provide a solid foundation in statistical modelling as applied in social research for both continuous and categorical data. The emphasis is on the underlying principles and uses of statistical models and not on the mathematical and statistical theory. Issues covered include selection of an appropriate model, the adequacy of a fitted model (in comparison to alternative models) and the statistical and substantive interpretation of models. SPSS will be used for practical work in developing models. Students will be introduced to STATA.
Learning Outcomes

By the end of the module the students should:

· Be familiar with the rationale and terminology of statistical modelling and to understand the logic of model development and testing

· Be able to develop multiple regression, logistic regression and multinomial logistic regression models using SPSS and to interpret the results

· To be familiar with other modelling techniques such as survival analysis and multilevel modelling

· To be aware of other statistical modelling software packages.
Module Content

· Description, definition of, and assumptions regarding statistical models

· The General Linear Model

· Models for a continuous response (multiple regression)

· Models for a binary response (logistic regression)

· Models for a categorical response (multinomial and ordered logistic regression)

· Implications for modelling when data are censored, hierarchical or from longitudinal studies.
Methods of Teaching/Learning
In addition to the formal lectures (which often become informal) there are practical classes at which students acquire skills with appropriate computer software and are able to seek clarification of concepts and methods.  The focus of the second half of the course is on building statistical models.
Selected Texts/Journals

Tarling, R. (2009) Statistical Modelling for Social Researchers, Principles and Practice, Routledge
Last Updated

April 2011