Gaussian Copula Regression Modeling for Marker Classification Metrics with Competing Risk Outcomes

Table 2

Empirical bias, standard error (SE), and mean square error (MSE) of the estimators of the parametric Gaussian copula regression model for simulations generated from Student copula, with sample sizes 200 and 400 and censoring distributions and .

Sample size and censoring	Parameters	Bias	SE	MSE
censoring		−0.1377	0.9418	0.9060
		0.0026	0.0871	0.0076
		0.0266	0.1092	0.0126
		−0.0138	0.7599	0.0577
		0.0050	0.0613	0.0038
		−0.0876	0.3737	0.1473
		−0.0260	0.0774	0.0067
		−0.0084	0.2302	0.0531
		−0.0151	0.2874	0.0828
		0.0008	0.0908	0.0082
		−0.0063	0.0678	0.0046
		0.0103	0.1062	0.0114
censoring		0.0665	0.7295	0.5366
		−0.0177	0.0710	0.0054
		0.0211	0.0886	0.0083
		0.0519	0.5557	0.3115
		0.0091	0.0423	0.0019
		−0.2629	0.3089	0.1646
		−0.0759	0.0651	0.0100
		−0.0193	0.1820	0.0335
		0.0156	0.2148	0.0464
		−0.0125	0.0619	0.0040
		0.0057	0.0479	0.0023
		−0.0017	0.0849	0.0072
censoring		0.0109	0.9646	0.9307
		−0.0154	0.0934	0.0090
		0.0280	0.1148	0.0140
		0.0264	0.7735	0.5990
		−0.0061	0.0677	0.0046
		−0.2373	0.4156	0.2290
		−0.0634	0.0860	0.0114
		0.0379	0.2350	0.0567
		−0.0492	0.3089	0.0979
		−0.0048	0.0940	0.0089
		0.0054	0.0670	0.0045
		−0.0101	0.1153	0.0134
censoring		−0.0146	0.6337	0.4018
		−0.0038	0.0636	0.0041
		0.0164	0.0678	0.0049
		0.0106	0.4484	0.2012
		−0.0025	0.0418	0.0018
		−0.0818	0.2821	0.0863
		−0.0208	0.0586	0.0039
		0.0084	0.1624	0.0264
		−0.0032	0.1945	0.0378
		−0.0083	0.0610	0.0038
		−0.0048	0.0462	0.0022
		0.0063	0.0759	0.0058