These workshops explored how numerical taxonomy techniques can be used both to construct classifications and, using longitudinal data sets, to explore the double dynamic of cases through a set of classifications and of changes in the classification system itself. The workshop began with a discussion of the logic of classification, following the approach adopted by Bowker and Star (1999). We then reviewed how numerical taxonomy procedures could be used with longitudinal data sets in order to explore trajectories through time. This format, of beginning with a conceptual discussion of the logic of enquiry, was common to all the workshops. There were two hands-on workshops. Next we asked particular participants (briefed in advance of the workshop) to present reflections on how numerical taxonomy might be useful in their own work. Finally we had a buzz group (small groups working together) and reported back plenary discussion of the approaches and their application. All discussions were recorded and processed interpretatively using NVIVO as the basis of our report on the workshop.
By following the links below, you can work through the course presentations and, by accessing the spss files on the left, you can then try out some of the techniques for yourself.
COURSE MATERIALS:
- Classification by David Byrne
- Fuzzy Clustering in Context by Wendy Olsen
- An example of doing a cluster analysis in a simple way
with continuous data by David Byrne - Hierarchical Cluster Analysis - Wards Method using binary data by Wendy Dyer