The Open UniversitySkip to content

Prediction regions for categorical variables

Gower, John and Harding, Simon A. (1998). Prediction regions for categorical variables. In: Blasius, Jörg and Greenacre, Michael eds. Visualization of Categorical Data. Elsevier Inc., pp. 405–419.

DOI (Digital Object Identifier) Link:
Google Scholar: Look up in Google Scholar


Quantitative information on two or more variables is often represented relative to coordinate axes. In this chapter we show how the familiar concepts associated with quantitative axes may be extended to categorical variables. We shall be concerned with low-dimensional approximations to high-dimensional representations relative to coordinate axes, and to understand the properties of the approximation we must first recapitulate the familiar properties of Cartesian coordinate axes. Figure 1 shows two coordinate axes referring to variables x1 and x2, marked with scales

Item Type: Book Chapter
Copyright Holders: 1998 Elsevier Inc.
ISBN: 0-12-299045-5, 978-0-12-299045-8
Academic Unit/Department: Mathematics, Computing and Technology > Mathematics and Statistics
Item ID: 24099
Depositing User: Sarah Frain
Date Deposited: 04 May 2011 10:39
Last Modified: 04 May 2011 10:39
Share this page:


Scopus Citations

Actions (login may be required)

View Item
Report issue / request change

Policies | Disclaimer

© The Open University   + 44 (0)870 333 4340