Skip to main content

Table 2 LCA model fit statistics

From: Identifying patterns of clinical conditions among high-cost older adult health care users using claims data: a latent class approach

Classes AIC BIC aBIC Entropy LMR BLRT
2 43,913.071 44,197.974 44,067.684 1  < 0.0001  < 0.0001
3 43,079.382 43,510.210 43,313.187 1  < 0.0001  < 0.0001
4 42,231.971 42,808.725 42,544.968 1  < 0.0001  < 0.0001
5 41,535.833 42,258.512 41,928.022 1  < 0.0001  < 0.0001
6 41,346.203 42,214.808 41,817.584 0.918  < 0.0001  < 0.0001
  1. AIC Akaike information criterion, BIC Bayesian information criterion, aBIC sample-size-adjusted BIC, LMR p-value for the Lo–Mendell–Rubin likelihood ratio test, BLRT p-value for the bootstrap likelihood ratio test, LCA latent class analysis