Prof Jonathan Jackson Col.8.05

The course is available to all research students.

The course will assume a knowledge of standard linear regression models, to the level covered in MY452/MY552 (Applied Regression Analysis)

An introduction to the application of modern multivariate methods used in the social sciences, with particular focus on latent variable models for continuous observed variables, and their application to questions of measurement in the social sciences. At least the following topics will be covered: principal components analysis, exploratory factor analysis, confirmatory factor analysis and structural equation models. In addition, a selection from the following topics will be covered: cluster analysis, correspondence analysis, multidimensional scaling, latent class models, latent trait models.

20 hours of lectures and 8 hours of computer workshops in the LT.

Exercises from the computer classes can be submitted for marking.

D J Bartholomew, F Steele, I Moustaki ; J I Galbraith (2008) Analysis of Multivariate Social Science Data (Second Edition).

Research project (100%).

Research paper 25-30 pages, including tables and figures, or approximately 3,000-4,000 words, answering a set of questions by applying multivariate analyses to some data (100%).