Table 2.

Standard errors (STE) of parameter estimates obtained by the QEM algorithm based on 10,000 simulated replicates. “S²” corresponds to an empirical sum of squares estimate of variance based on a sample of point estimates of respective regression coefficients. Other types of STE estimators are based on inverted information matrices I⁻¹ and ${\mathcal{I}}_{\mathrm{CD}}^{-1}$.

	Contrasts
Variables	2 vs. 1			3 vs. 1			4 vs. 1
	S2	I−1	${\mathcal{I}}_{\mathrm{CD}}^{-1}$	S2	I−1	${\mathcal{I}}_{\mathrm{CD}}^{-1}$	S2	I−1	${\mathcal{I}}_{\mathrm{CD}}^{-1}$
Intercept	0.16	0.15	0.12	0.14	0.13	0.10	0.17	0.17	0.12
z1	0.14	0.14	0.10	0.12	0.12	0.09	0.15	0.15	0.07
z2	0.13	0.13	0.08	0.10	0.10	0.07	0.10	0.10	0.06
z3	0.27	0.26	0.21	0.19	0.19	0.14	0.21	0.21	0.12