Table 3.

Simulation results for LCA with a binary distal outcome: Bias in proportion with Z = 1 given latent class membership

		Moderate Measurement					Strong Measurement
		Latent Class					Latent Class
Method	ES	1	2	3	4	5	1	2	3	4	5
		n = 500
Model	Zero	−0.003	−0.000	0.009	0.005	0.006	−0.000	0.002	0.002	0.002	−0.002
Assign	Zero	−0.002	0.001	0.002	0.002	0.004	−0.000	0.002	0.003	0.002	−0.002
P-C	Zero	−0.002	0.000	0.003	0.002	0.004	−0.000	0.002	0.002	0.002	−0.001
Model	Sm	−0.000	0.001	−0.017	−0.017	−0.009	−0.000	−0.001	−0.012	−0.009	−0.003
Assign	Sm	0.008	0.007	−0.025	−0.031	−0.025	0.003	0.002	−0.017	−0.014	−0.007
P-C	Sm	0.010	0.008	−0.027	−0.034	−0.030	0.003	0.002	−0.018	−0.015	−0.009
Model	Med	0.001	0.005	−0.033	−0.072	−0.023	0.000	0.001	−0.030	−0.028	−0.005
Assign	Med	0.023	0.020	−0.066	−0.097	−0.078	0.009	0.006	−0.050	−0.041	−0.018
P-C	Med	0.028	0.020	−0.071	−0.104	−0.091	0.010	0.006	−0.053	−0.044	−0.022
Model	Lg	0.010	0.003	−0.037	−0.115	−0.029	0.001	−0.001	−0.034	−0.027	−0.008
Assign	Lg	0.039	0.028	−0.103	−0.150	−0.113	0.012	0.008	−0.074	−0.056	−0.026
P-C	Lg	0.046	0.030	−0.111	−0.159	−0.135	0.013	0.009	−0.080	−0.061	−0.032
		n = 1000
Model	Zero	−0.000	−0.001	0.003	−0.002	0.001	0.001	−0.000	0.001	0.003	0.001
Assign	Zero	0.000	−0.000	0.002	−0.003	0.001	0.002	−0.000	0.000	0.002	0.001
P-C	Zero	0.000	−0.000	0.002	−0.002	0.000	0.001	0.000	0.001	0.002	0.001
Model	Sm	−0.003	0.001	−0.013	−0.011	−0.004	0.000	−0.002	−0.014	−0.009	0.000
Assign	Sm	0.008	0.007	−0.023	−0.023	−0.021	0.003	0.001	−0.019	−0.014	−0.004
P-C	Sm	0.009	0.006	−0.025	−0.027	−0.028	0.003	0.001	−0.020	−0.015	−0.006
Model	Med	−0.001	−0.001	−0.030	−0.040	−0.008	0.001	−0.002	−0.020	−0.019	−0.003
Assign	Med	0.023	0.015	−0.070	−0.077	−0.061	0.009	0.006	−0.048	−0.037	−0.016
P-C	Med	0.028	0.015	−0.075	−0.086	−0.079	0.010	0.006	−0.051	−0.041	−0.021
Model	Lg	0.003	−0.002	−0.016	−0.061	−0.010	0.000	0.001	−0.018	−0.022	−0.005
Assign	Lg	0.035	0.022	−0.105	−0.115	−0.091	0.012	0.011	−0.075	−0.056	−0.024
P-C	Lg	0.042	0.023	−0.112	−0.130	−0.120	0.013	0.010	−0.081	−0.062	−0.032

Note: Model = model-based approach; Assign = maximum-probability assignment rule; P-C = multiple pseudo-class draws.