Skip to main content

Table 1 Model fit indices for latent profiles of food combinations at breakfast eating occasionsa

From: What do Australian adults eat for breakfast? A latent variable mixture modelling approach for understanding combinations of foods at eating occasions

  2 classes 3 classes 4 classes 5 classes 6 classes
Men
 Loglikelihood −60,711.023 −59,309.719 −58,281.212 −57,825.658 − 57,424.792
 Entropy 0.819 0.873 0.872 0.868 0.849
 BIC 122,871.330 120,642.489 119,181.015 118,854.561 118,637.483
 adjusted BIC 122,312.086 119,857.641 118,170.563 117,618.505 117,175.822
bLMR-LRT 5586.967, P < 0.001 2808.885, P < 0.001 2042.776, P < 0.001 912.682, P = 0.01 794.951, P = 0.08
Women
 Loglikelihood −67,230.626 −65,773.386 −64,449.367 −63,598.615 −63,454.789
 Entropy 0.863 0.881 0.878 0.926 0.889
 BIC 135,936.216 133,617.594 131,564.811 130,458.564 130,766.168
 adjusted BIC 135,376.959 132,832.727 130,554.335 129,222.479 129,304.474
bLMR-LRT 6122.822, P = 0.12 2900.629, P < 0.0001 2643.024, P < 0.0001 1742.887, P < 0.0001 336.794, P = 0.13
  1. aAIC Akaike Information Criterion, BIC Bayesian Information Criterion, BS Bootstrap, LMR Lo-Mendell-Rubin, LRT likelihood ratio test
  2. bAdjusted Lo-Mendell-Rubin likelihood ratio test for k versus k-1 profiles. Values are two times the loglikelihood difference and corresponding p-value