This is an implementation of Leo Breiman's twonorm example[1]. It is a 20 dimensional, 2 class classification example. Each class is drawn from a multivariate normal distribution with unit variance. Class 1 has mean (a,a,..a) while Class 2 has mean (-a,-a,..-a). Where a = 2/sqrt(20). Breiman reports the theoretical expected misclassification rate as 2.3%. He used 300 training examples with CART and found an error of 22.1%.
Origin: artificial
Usage: historical
Number of attributes: 21
Number of cases: 7,400
Number of prototasks: 1
Number of methods run on this dataset: 3
Download twonorm.tar.gz
Contributed by: Michael Revow.
Last Updated 11 October 1996 Comments and questions to: delve@cs.toronto.edu |