|
Activity Number:
|
42
|
|
Type:
|
Invited
|
|
Date/Time:
|
Sunday, August 3, 2008 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Section on Statistical Graphics
|
| Abstract - #300389 |
|
Title:
|
Scagnostics and Related Techniques for Automodeling-Based Visualization
|
|
Author(s):
|
Leland Wilkinson and Graham Wills*+
|
|
Companies:
|
Northwestern University and SPSS, Inc
|
|
Address:
|
, Chicago, IL, ,
|
|
Keywords:
|
visualization ; statistical graphics
|
|
Abstract:
|
When faced with a data set that is both wide and long, it can be a challenge to see even a simple overview of the data. Validating data, transforming it and understanding simple univariate structures is both tedious and error-prone. With hundreds or thousands of variables, when we move beyond univariate analysis to multivariate analysis, some form of automatic aid becomes necessary. In this talk we introduce Tukey and Tukey scagnostics and develop graph theoretic methods for implementing their procedure on large datasets. We describe a prototype automatic modeling system (for a very loose definition of 'modeling') and explore its advantages and deficiencies for the automatic modeling of large data sets.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2008 program |
