Table 5.

Simulation results for LCA with a count distal outcome: Bias in mean count 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	−0.005	0.003	0.015	0.004	0.014	−0.000	−0.000	0.002	−0.004	−0.003
Assign	Zero	−0.002	0.003	0.007	0.001	0.007	0.000	−0.001	0.001	−0.003	−0.003
P-C	Zero	−0.001	0.002	0.006	0.001	0.008	−0.000	−0.001	0.001	−0.002	−0.003
Model	Sm	0.003	−0.001	−0.035	−0.062	−0.025	−0.002	0.001	−0.029	−0.020	−0.008
Assign	Sm	0.019	0.012	−0.051	−0.074	−0.064	0.005	0.007	−0.039	−0.027	−0.018
P-C	Sm	0.022	0.011	−0.055	−0.076	−0.073	0.006	0.006	−0.042	−0.029	−0.021
Model	Med	0.001	−0.001	−0.065	−0.133	−0.051	0.001	−0.000	−0.052	−0.060	−0.002
Assign	Med	0.047	0.032	−0.132	−0.189	−0.155	0.018	0.012	−0.093	−0.086	−0.030
P-C	Med	0.056	0.035	−0.142	−0.201	−0.182	0.020	0.012	−0.099	−0.093	−0.036
Model	Lg	0.004	0.010	−0.072	−0.217	−0.060	0.000	−0.001	−0.060	−0.064	−0.002
Assign	Lg	0.083	0.062	−0.222	−0.323	−0.241	0.027	0.019	−0.167	−0.124	−0.046
P-C	Lg	0.099	0.065	−0.235	−0.345	−0.288	0.029	0.019	−0.180	−0.135	−0.059
		n = 1000
Model	Zero	0.005	−0.001	−0.004	0.000	−0.003	−0.001	−0.002	0.001	0.002	−0.001
Assign	Zero	0.003	−0.001	−0.003	−0.002	−0.002	−0.000	−0.001	0.000	0.002	0.000
P-C	Zero	0.002	−0.000	−0.002	−0.001	−0.001	−0.000	−0.002	0.001	0.002	−0.000
Model	Sm	−0.005	0.001	−0.030	−0.039	0.003	−0.002	0.001	−0.019	−0.023	0.003
Assign	Sm	0.015	0.012	−0.051	−0.056	−0.039	0.005	0.007	−0.033	−0.031	−0.008
P-C	Sm	0.019	0.013	−0.055	−0.062	−0.052	0.006	0.006	−0.036	−0.034	−0.012
Model	Med	−0.007	−0.001	−0.048	−0.080	−0.011	−0.002	−0.003	−0.038	−0.038	−0.002
Assign	Med	0.044	0.030	−0.131	−0.145	−0.118	0.016	0.012	−0.093	−0.077	−0.029
P-C	Med	0.054	0.032	−0.141	−0.166	−0.153	0.018	0.011	−0.102	−0.084	−0.040
Model	Lg	−0.001	0.003	−0.030	−0.133	−0.029	−0.001	−0.002	−0.029	−0.044	−0.007
Assign	Lg	0.075	0.049	−0.219	−0.252	−0.201	0.026	0.020	−0.158	−0.128	−0.050
P-C	Lg	0.091	0.050	−0.237	−0.285	−0.264	0.028	0.018	−0.171	−0.139	−0.068

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