Table 1.
No. of classes | Fit estimatesa | P valuesb | Entropyc | ||||
AICd | BICe | adj.BICf | Vuong-Lo- Mendell-Rubin likelihood ratio test | Lo-Mendell- Rubin adjusted likelihood ratio test | Bootstrap likelihood ratio test | ||
1 | 5798 | 5825 | 5800 | ||||
2 | 5742 | 5783 | 5745 | <.01 | <.01 | <.01 | .69 |
3 | 5709 | 5764 | 5714 | .23 | .24 | <.01 | .77 |
4 | 5673 | 5742 | 5679 | .06 | .07 | <.01 | .85 |
5 | 5647 | 5730 | 5654 | .24 | .26 | <.01 | .86 |
6 | 5630 | 5727 | 5638 | .08 | .10 | <.01 | .87 |
aLower values of AIC, BIC, and adj.BIC indicate better model fit.
bP values for test against model minus 1 class.
cEntropy estimates ranges from 0 to 1 and assess the accuracy with which models classify individuals into their most likely class; higher scores represent greater classification accuracy.
dAkaike information criteria.
eBayesian information criteria.
fSample size-adjusted BIC.