Skip to main content
. Author manuscript; available in PMC: 2023 Aug 1.
Published in final edited form as: Psychol Addict Behav. 2022 Jan 27;36(5):515–525. doi: 10.1037/adb0000817

Table 1.

Model fit and classification diagnostics of exploratory latent profile analysis with class-invariant diagonal variance-covariance matrix.

Number of classes tested LL BIC SSABIC AIC CAIC AWE LMR LRT: p-value Entropy
1-Class −10186.61 20738.68 20535.71 20501.22 20802.68 21296.15 - -
2-Class −8334.85 17223.62 16915.98 16863.70 17320.62 18068.53 0.174 0.923
3-Class −7411.61 15565.58 15153.30 15083.23 15695.58 16697.94 0.419 0.949
4-Class −6943.44 14817.67 14300.73 14212.87 14980.67 16237.47 0.439 0.961
5-Class −6559.43 14238.10 13616.50 13510.86 14434.10 15945.35 0.757 0.946

Notes: LL=“Log Likelihood”, BIC=“Bayesian Information Criterion”, SSABIC=“Sample Size Adjusted Bayesian Information Criterion”, AIC=“Akaike’s Information Criterion” CAIC=“Consistent Akaike’s Information Criterion”, AWE=“Approximate Weight of Evidence Criterion”, LMR LRT=“ Lo-Mendell-Rubin likelihood ratio test”