Skip to main content

Table 3 Hypothetical data for two ordered markers, A and B

From: Markers for early detection of cancer: Statistical guidelines for nested case-control studies

 

Subjects without cancer (N = 1000)

Subjects with cancer (N = 100)

 

A = 1

A = 2

A = 3

B only

A = 1

A = 2

A = 3

B only

B = 1

640

80

80

800

20

0

0

20

B = 2

80

10 a

10 a

100 e

0

20 b

0 b

20 f

B = 3

80

10 a

10 a

100 e

0

0 b

60 b

60 f

A only

800

100 c

100 c

 

20

20 d

60 d

 
  1. For A and B combined; aFalse positive rate (FPR) of indicated region (10+10+10+10)/1000=. 04; bTrue positive rate (TPR) of indicated region = (20 +0+0+60)/100=. 80 For A only; cFalse positive rate (FPR) of indicated region =(100+100)/1000=. 20; dTrue positive rate (TPR) of indicated region = (20+60)/100=. 80 For B only; eFalse positive rate (FPR) of indicated region =(100+100)/1000= .20; fTrue positive rate (TPR) of indicated region = (20+60)/100=.80