Skip to main content
. 2016 Mar 1;11(3):e0150563. doi: 10.1371/journal.pone.0150563

Table 2. IRT Mixture Analyses of the Pain Item Bank.

Class proportions*
K P LL BIC LR VLMR p-value BLRT p-value Entropy C1 C2 C3
1 177 -43285.9 87884 1.00
2 354 -41715.4 86056 3141 .000 .000 .86 .59 .41
3 531 -40858.6 85654 1713 .000 .000 .83 .27 .30 .43

Notes. N = 1,660. K = Number of latent classes in the model. P = number of parameters. LL = log likelihood. BIC = Bayesian Information Criterion. LR = Likelihood ratio of GRM and 2-, and 3-class LVMMs. VLMR = Vuong-Lo-Mendel-Rubin likelihood ratio test p-value. BLRT = Bootstrapped likelihood ratio test p-value. C1-C3 = classes 1 through 3.

* Probability of latent class membership predicted by the model.