We propose a methodology for finding the empirical distribution of the Rand's measure of association when the two partitions only differ by chance. For that purpose we simulate data coming from a latent profile model and we partition them according to 2 groups of variables. We also study two other indices: the first is based on an adaptation of Mac Nemar' test, the second being Jaccard' index. Surprisingly, the distributions of the 3 indices are bimodal.
@article{hal-01124747,
author = {Saporta, Gilbert and Youness, Genane},
title = {Comparing two partitions: Some Proposals and Experiments},
journal = {HAL},
volume = {2002},
number = {0},
year = {2002},
language = {en},
url = {http://dml.mathdoc.fr/item/hal-01124747}
}
Saporta, Gilbert; Youness, Genane. Comparing two partitions: Some Proposals and Experiments. HAL, Tome 2002 (2002) no. 0, . http://gdmltest.u-ga.fr/item/hal-01124747/