Skip to main content
. Author manuscript; available in PMC: 2018 Apr 1.
Published in final edited form as: J Youth Adolesc. 2016 Nov 26;46(4):826–839. doi: 10.1007/s10964-016-0619-7

Table 4.

Fit Indices for Unconditional Growth Mixture Models Identifying Latent Anxiety Symptom Trajectories in Adolescent Girls and Boys

Latent
Classes
Parameters LL BIC cAIC LMR-LRT
(p value)
Entropy
Generalized Anxiety Disorder Symptoms
1 5 −5361.27 10756.13 10761.13 -- 1.00
2 8 −5206.97 10467.67 10475.67 < .001 0.79
3 11 −5150.41 10374.71 10385.71 < .001 0.74
4 14 −5134.75 10363.55 10377.55 .02 0.73
5 17 −5127.05 10368.30 10385.30 .34 0.74
6 20 −5117.04 10368.44 10388.44 .17 0.74

Social Anxiety Disorder Symptoms
1 5 −4987.45 10008.48 10013.48 -- 1.00
2 8 −4855.88 9765.50 9773.50 < .001 0.70
3 11 −4795.90 9665.69 9676.69 < .001 0.76
4 14 −4775.22 9644.49 9658.49 .002 0.79
5 17 −4758.65 9631.49 9648.49 .01 0.76
6 20 −4749.47 9633.29 9653.29 .19 0.77

Note: BIC = Bayesian Information Criterion; cAIC = Consistent Akaike Information Criterion; LL = Log-likelihood; LMR-LRT = Lo-Mendell-Rubin Likelihood Ratio Test; Lower BIC and cAIC values indicated better model fit. LMR-LRT p values ≤ .05 indicated that the k-class solution was a superior fit compared to a k-1 class solution. Entropy provided a measure of classification accuracy, with higher values indicating better accuracy.

The bolded numbers represent the lowest values of each information-based fit index.