School Seminars and Colloquia

From the Statistics of Data to the Statistics of Knowledge: Symbolic Data Analyses

Applied Statistics Seminar

by Lynne Billard


Institution: University of Georgia (USA)
Date: Fri 29th July 2005
Time: 4:15 PM
Location: Old Geology Theatre 2

Abstract: With the advent of computers, large, very large datasets have
become routine. What is not so routine is how to analyse these data
and/or how to glean useful information from within their massive
confines. One approach is to summarize large data sets in such a way
that the resulting summary dataset is of a manageable size. One
consequence of this is that the data may no longer be formatted as
single values such as is the case for classical data, but may be
represented by lists, intervals, distributions and the like. Thus,
a symbolic-valued 'observation' is a p-dimensional hypercube and/or
Cartesian products of distributions in contrast to a classical
observation which is a single point in p-dimensional space. This
talk will look at the concept of symbolic data in general, and will
attempt to review methods currently available to analyse such data.

For More Information: Owen Jones tel: 8344 6412 email: O.Jones@ms.unimelb.edu.au