TABLE 1. Fit Criteria for Each Model Specification.

Model	Number of Level 1 Classes
	1 Class	2 Classes	3 Classes	4 Classes	5 Classes	6 Classes
1. Fixed effects model
No. of free parameters	8	17	26	35	44	53
Log-likelihood	−41,813	−31,013	−29,204	−29,090	−29,057	−29,040
BIC	83,700	62,185	58,650	58,505	58,523	58,572
Lo–Mendell–Rubin LRT	N/A	21,343	3,575	226	65	34
Entropy	1.00	0.98	0.96	0.76	0.73	0.73
2. Random effects model, parametric
No. of free parameters		18	29	41
Log-likelihood		−30,769	−28,902	−28,694
BIC		61,705	58,074	57,768
Entropy		0.98	0.96	0.77
3. Random effects model, parametric with factor on the Level 2 random intercepts
No. of free parameters		N/A	28	38
Log-likelihood			−28,916	−28,713
BIC			58,093	57,779
Entropy			0.96	0.77
4. Random effects model, nonparametric
4a. 2 between classes
No. of free parameters		19	29	39
Log-likelihood		−30,825	−28,984	−28,800
BIC		61,827	58,236	57,961
Entropy		0.91	0.92	0.81
4b. 3 between classes
No. of free parameters		21	32	43
Log-likelihood		−30,792	−28,944	−28,746
BIC		61,778	58,185	57,892
Entropy		0.91	0.90	0.79
5. Random effects model, parametric with factor on Level 1 latent class indicators
No. of free parameters		25	37	a
Log-likelihood		−30,422	−28,737
BIC		61,076	57,817
Entropy		0.98	0.96
6. Random effects model, parametric with factor on Level 1 latent class indicators and factor on Level 2 random intercepts
No. of free parameters		N/A	35	45
Log-likelihood			−28,751	−28,652
BIC			57,827	57,722
Entropy			0.96	0.75
7. Random effects model, nonparametric with factor on Level 1 latent class indicators
7a. 2 between classes
No. of free parameters		26	36	46
Log-likelihood		−30,482	−28,833	−28,728
BIC		61,206	58,000	57,883
Entropy		0.91	0.92	0.87
7b. 3 between classes
No. of free parameters		29	40	51
Log-likelihood		−30,447	−28,785	−28,687
BIC		61,162	57,942	57,848
Entropy		0.91	0.91	0.88

Note. BIC = Bayesian information criterion; LRT = likelihood ratio test;

^aModel is too computationally intensive to estimate.

N/A = not applicable