. 2014 Sep 29;5:1087. doi: 10.3389/fpsyg.2014.01087

Table 3.

Bias detection with the single run procedure.

		Cond.	Conv.	Biased items^a					Unbiased items^b
				Δ DIC			TP		Δ DIC			FP
				Q₀₅	Q₅₀	Q₉₅	Strict	Liberal	Q₀₅	Q₅₀	Q₉₅	Strict	Liberal
CONTINUOUS LATENT VIOLATOR
ρ(T,V) = 0.0	No bias	1	0.73	–	–	–	–	–	−10	0	0	0.304	0.014
	Uniform	2	0.45	−100	−70	−42	1.000	1.000	−20	0	0	0.387	0.093
	Nonuniform	3	0.67	−110	−70	−40	1.000	1.000	−20	0	0	0.382	0.063
	Both	4	0.52	−185	−125	−86	1.000	1.000	−20	0	0	0.423	0.096
ρ(T,V) = 0.5	No bias	5	0.75	–	–	–	–	–	−10	0	0	0.282	0.020
	Uniform	6	0.74	−80	−50	−27	1.000	1.000	−20	0	0	0.432	0.081
	Nonuniform	7	0.78	−140	−85	−40	1.000	1.000	−20	0	0	0.426	0.079
	Both	8	0.75	−193	−130	−70	1.000	1.000	−20	−10	0	0.528	0.157
CONTINUOUS OBSERVED VIOLATOR
ρ(T,V) = 0.0	No bias	9	0.96	–	–	–	–	–	−8	−2	0	0.776	0.016
	Uniform	10	0.88	−103	−71	−50	1.000	1.000	−13	−3	0	0.748	0.093
	Nonuniform	11	0.89	−110	−71	−44	1.000	1.000	−12	−3	0	0.742	0.079
	Both	12	0.88	−175	−138	−93	1.000	1.000	−14	−4	0	0.764	0.143
ρ(T,V) = 0.5	No bias	13	0.28	–	–	–	–	–	−8	−2	0	0.756	0.030
	Uniform	14	0.07	−68	−52	−34	1.000	1.000	−14	−2	0	0.657	0.171
	Nonuniform	15	0.18	−106	−77	−46	1.000	1.000	−12	−3	0	0.722	0.100
	Both	16	0.08	−147	−124	−96	1.000	1.000	−18	−7	0	0.750	0.300
DICHOTOMIZED OBSERVED VIOLATOR
ρ(T,V) = 0.0	No bias	17	0.99	–	–	–	–	–	−9	−2	0	0.791	0.022
	Uniform	18	0.99	−70	−45	−28	1.000	1.000	−12	−2	0	0.739	0.089
	Nonuniform	19	0.99	−73	−45	−22	1.000	1.000	−11	−3	0	0.737	0.057
	Both	20	0.96	−119	−88	−55	1.000	1.000	−13	−3	0	0.760	0.104
ρ(T,V) = 0.5	No bias	21	0.69	–	–	–	–	–	−8	−2	0	0.775	0.017
	Uniform	22	0.38	−56	−28	−14	1.000	0.974	−11	−3	0	0.758	0.058
	Nonuniform	23	0.62	−78	−50	26	1.000	1.000	−11	−3	0	0.745	0.055
	Both	24	0.32	−118	−84	−54	1.000	1.000	−16	−4	0	0.756	0.131

Cond., Condition; Conv., proportion of converged solutions; Δ DIC denotes the difference in DIC between the reference model and the competing model;

Quantile DIC difference values (i.e., 05, 50, 95), and proportions of true positives (TP) are calculated over the converged solutions [of 1 (biased item) × 100 (replicates) = 100 solutions];

Quantile DIC values (i.e., 05, 50, 95), and proportions of false positives (FP) are calculated over the converged solutions, which are 6 (non-biased items) × 100 (replicates) = 600 solutions in Conditions 1, 5, 9, 13, 17 and 21, and 5 (non-biased items) × 100 (replicates) = 500 solutions in all other conditions.