Table 1.

Coverage probability (CP) and mean squared error (MSE) for the N = 50 arm of the simulation study. Nominal coverage probability is 95%. We compare treating the data as independent within a subject (“Ind”), fitting with a copula (“Cop”), and the random effects model of (Reich, Bondell and Wang, 2010) (“RBW”). Coverage and MSE were evaluated at and averaged over the quantile levels {0.1, 0.3, 0.5, 0.7, 0.9}. For datatype = 1, MSE values are less than depicted values by a factor of 10. Estimators whose MSE were statistically significantly different than the copula model are indicated by*.

Δ = 0, Datatype = 1
	Coverage						MSE
	α = 0.0		α = 0.5		α = 0.9		α = 0.0		α = 0.5		α = 0.9
	X1	X2	X1	X2	X1	X2	X1	X2	X1	X2	X1	X2
Ind	0.91	0.95	0.88	0.94	0.73	0.94	0.05	0.09	0.07	0.10	0.11	0.11
Cop	0.95	0.96	0.95	0.97	0.94	0.96	0.05	0.10	0.06	0.10	0.09	0.10
RBW	0.83	0.90	0.86	0.89	0.88	0.87	0.11*	0.16*	0.13*	0.15*	0.16*	0.14*
Δ = 0, Datatype = 2
	Coverage						MSE
	α = 0.0		α = 0.5		α = 0.9		α = 0.0		α = 0.5		α = 0.9
	X1	X2	X1	X2	X1	X2	X1	X2	X1	X2	X1	X2
Ind	0.94	0.97	0.89	0.94	0.76	0.95	0.06	0.09	0.09	0.11	0.15	0.13
Cop	0.98	0.98	0.95	0.98	0.93	0.97	0.07	0.11	0.10	0.13	0.16	0.13
RBW	0.96	0.98	0.95	0.96	0.93	0.95	0.07	0.10	0.10	0.11	0.14	0.10
Δ = 3, Datatype = 1
	Coverage						MSE
	α = 0.0		α = 0.5		α = 0.9		α = 0.0		α = 0.5		α = 0.9
	X1	X2	X1	X2	X1	X2	X1	X2	X1	X2	X1	X2
Ind	0.61	0.76	0.58	0.78	0.56	0.72	0.17	0.24	0.19	0.25*	0.23	0.24*
Cop	0.92	0.91	0.91	0.90	0.89	0.91	0.14	0.18	0.15	0.17	0.18	0.17
RBW	0.85	0.70	0.85	0.69	0.86	0.67	0.23*	0.26*	0.24	0.26*	0.25	0.24*
Δ = 3, Datatype = 2
	Coverage						MSE
	α = 0.0		α = 0.5		α = 0.9		α = 0.0		α = 0.5		α = 0.9
	X1	X2	X1	X2	X1	X2	X1	X2	X1	X2	X1	X2
Ind	0.64	0.76	0.60	0.78	0.57	0.74	0.26	0.26	0.28	0.25	0.32*	0.29*
Cop	0.90	0.90	0.89	0.89	0.91	0.92	0.21	0.21	0.20	0.21	0.19	0.17
RBW	0.86	0.80	0.84	0.79	0.83	0.77	0.26	0.21	0.26	0.22	0.31*	0.24