Detecting Falsified Financial Statements Using a Hybrid SM-UTADIS Approach : Empirical Analysis of Listed Traditional Chinese Medicine Companies in China

Table 10

Error summary with SM-logistic regression method.

Data	Actual class	Total amount	Number of errors identified	Type I errors	Type II errors (%)	Overall errors (%)
Training dataset	C1	12	1	0	8.3333	5.5556
	C2	6	0
Testing dataset	C1	12	3	33.3333%	25.0000	27.7778
	C2	6	2