Data Reduction and Classification
Dates: 28th April 2011
Duration: 1 day (10am — 4:30pm)
Level: Advanced
Course Fee: £175 (£125 for those from educational institutions)
CCSR offer 5 free places to research staff and students within the Faculty of Humanities at the University of Manchester.
Course Leader:
Mark Tranmer
Course Requirements:
Familiarity with SPSS for Windows. Some experience of introductory data analysis desirable.
Course Summary
This one-day course discusses various methods of data reduction, focusing on the use of principal components analysis (PCA). SPSS is used to apply PCA to UK Census data. Although factor analysis is also discussed briefly in the data reduction part of the course, the focus is on the use of PCA data reduction methods to construct a deprivation score.
We also consider data classification focusing on the theory and application of cluster analysis. We look at an example based on UK Census data and use SPSS to carry out a cluster analysis using both hierarchical and k-means approaches.
Course Objectives
- Introduce the general ideas of data reduction and classification from a social science perspective.
- Show how these techniques can be applied using SPSS with examples from the UK census.
Target Audience
Social scientists with some experience of introductory data analysis.
Preliminary Reading
Snijders and Bosker (1999) Multilevel modelling. Sage.