Skip to main content
. 2022 Nov 25;26:363. doi: 10.1186/s13054-022-04251-2

Table 2.

Model-fit statistics for different numbers of latent classes

Classes No. of patients per class BIC LMR-LRT LMR-LRT p value Entropy
1 99 3469.681
2 62, 37 3444.222 130.8  < 0.001 0.75
3 53, 19, 27 3454.702 97.3  < 0.001 0.88
4 18, 43, 35, 13 3484.582 79.2  < 0.001 0.91
5 36, 22, 13, 14, 14 3539.557 55.9  < 0.001 0.93

BIC Bayesian information criterion. LMR-LRT Lo–Mendell–Rubin adjusted likelihood ratio test