. 2015 Oct 30;15:49. doi: 10.1186/s12880-015-0083-y

Table 5.

Estimated parameters, Goodness-of-fit statistics and dose reduction of GWrank

Model	Coefficient						Goodness-of-fit		Dose Reduction
Model	logCTDI		id2		id4		AIC	Pseudo R²	id2	id4
	Est.	P-value	Est.	P-value	Est.	P-value	AIC	Pseudo R²	id2	id4
regress^a	4.482	<0.001	0.850	<0.001	0.696	<0.001	-	0.0959	17.27 %	14.38 %
regress^a	(3.981, 4.983)		(0.673, 1.027)		(0.518, 0.873)		-	0.0959	(14.44 %, 20.11 %)	(11.44 %, 17.32 %)
ologit^a	9.247	<0.001	1.780	<0.001	1.531	<0.001	2462.68	0.1138	17.51 %	15.26 %
ologit^a	(8.126, 10.368)		(1.428, 2.132)		(1.168, 1.894)		2462.68	0.1138	(14.99 %, 20.02 %)	(12.51 %, 18.01 %)
rologit^a	5.537	<0.001	1.232	<0.001	0.932	<0.001	1303.66	0.1493	19.95 %	15.49 %
rologit^a	(4.734, 6.340)		(0.969, 1.495)		(0.666, 1.197)		1303.66	0.1493	(17.06 %, 22.84 %)	(12.24 %, 18.74 %)
mixed^b	4.482	<0.001	0.850	<0.001	0.696	<0.001	2670.66	0.0000	17.27 %	14.38 %
mixed^b	(3.995, 4.970)		(0.677, 1.023)		(0.523, 0.869)		2670.66	0.0000	(14.51 %, 20.04 %)	(11.51 %, 17.24 %)
meologit^b	9.267	<0.001	1.751	<0.001	1.549	<0.001	2452.89	0.0320	17.22 %	15.40 %
meologit^b	(8.991, 9.543)		(1.416, 2.086)		(1.214, 1.885)		2452.89	0.0320	(14.36 %, 20.07 %)	(12.43 %, 18.36 %)

95 % confidence limits of each estimate given in parentheses

^aregression model with fixed effects only

^bregression model with fixed and random effects