Measures of Imbalance for Unbalanced Models.
Abstract
This paper presents a procedure to measure the degree of imbalance of an unbalanced data set. The procedure is based on choosing an appropriate loglinear model for the subclass frequencies of the data. A measure of imbalance is then introduced as some function of the chi-squared statistic used in the goodness-of-fit test for the loglinear model. The proposed procedure can also be used to measure departures from certain types of balancce, such as proportionality of subclass frequencies, partial balance, and last-stage uniformity. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1986
- Accession Number
- ADA164638
Entities
People
- Andre' I. Khuri
Organizations
- University of Florida