Rough Sets Data Analysis in Knowledge Discovery: A Case of Kuwaiti Diabetic Children Patients

Table 10

Discriminant analysis classification results (93.3% of original grouped cases correctly classified; 91.9% of cross-validated grouped cases correctly classified).

			Predicted group membership
		Totalcode	Normal	Borderline	Abnormal
Original	Count	normal	88	4	0	92
		borderline	11	28	3	42
		abnormal	0	2	162	164
	%	normal	95.7	4.3	.0	100.0
		borderline	26.2	66.7	7.1	100.0
		abnormal	.0	1.2	98.8	100.0
Cross-validated^a	Count	normal	87	5	0	92
		borderline	12	26	4	42
		abnormal	0	3	161	164
	%	normal	94.6	5.4	.0	100.0
		borderline	28.6	61.9	9.5	100.0
		abnormal	.0	1.8	98.2	100.0

^aCross-validation is done only for those cases in the analysis. In cross validation, each case is classified by the functions derived from all cases other than that case.