The scale of the test variable XX ranges from 1-14, without decimals. So why does the scale of variable in question look like this in the SPSS output (see below)? Moreover, if specificity and sensitivity are considered about equally important, what cut off point would you recommend? XX ≥ ??
Coordinates of the Curve
Positive if
Greater Than
or Equal to Sensitivity 1 - Specificity
-1,00 1,000 1,000
0,50 ,995 ,982
1,50 ,993 ,815
2,50 ,976 ,614
3,50 ,953 ,418
4,50 ,900 ,240
5,50 ,845 ,110
6,50 ,688 ,018
7,50 ,562 ,000
8,50 ,382 ,000
9,50 ,277 ,000
10,50 ,154 ,000
11,50 ,098 ,000
13,00 ,000 ,000
If used a positive cutoff => 4,50, it will screen positive in 90% of affected populations, specificity is 76%, but it has 24% false negative. While a cutoff => 5,50, it will screen positive in 84.5% of affected ones, 89% specific and it has 11% false negative. Better to use the second cutoff 5,50, more specific & sensitive one.
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS