Table 1.

Cross-validation forward.

	Training sample size (%)	TP	TN	FP	FN	Sensitivity	Specificity	Accuracy
Binary logistic regression	0.4	82371	11148	2852	5629	0.9360	0.7963	0.9169
	0.6	53525	7547	1453	4475	0.9228	0.8386	0.9115
	0.8	26657	4289	711	2343	0.9192	0.8578	0.9102
SVM	0.4	83580	9666	4334	4420	0.9498	0.6904	0.9142
	0.6	55035	6761	2239	2965	0.9489	0.7512	0.9223
	0.8	27677	3868	1132	1323	0.9544	0.7736	0.9278
LDA	0.4	82465	11603	2397	5535	0.9371	0.8288	0.9222
	0.6	54676	7510	1490	3324	0.9427	0.8344	0.9281
	0.8	27483	4159	841	1517	0.9477	0.8318	0.9306
QDA	0.4	82687	6647	7353	5313	0.9396	0.4748	0.8758
	0.6	52177	6695	2305	5823	0.8996	0.7439	0.8787
	0.8	25860	4064	936	3140	0.8917	0.8128	0.8801
Neural Networks	0.4	86408	10132	4830	1592	0.9819	0.6772	0.9376
	0.6	56932	6819	2181	1068	0.9816	0.7577	0.9515
	0.8	28535	3828	1172	465	0.9840	0.7656	0.9519
Classification Trees	0.4	80945	3508	10492	7055	0.9198	0.2506	0.8280
	0.6	53202	2554	6446	4798	0.9173	0.2838	0.8322
	0.8	26804	1354	3646	2196	0.9243	0.2708	0.8282
Boosting Trees	0.4	84585	4921	9153	3415	0.9612	0.3497	0.8769
	0.6	55461	3278	5918	2539	0.9562	0.3565	0.8741
	0.8	27708	1668	4580	1292	0.9554	0.2670	0.8334