Skip to main content
. 2018 Jun 8;45(3):600–609. doi: 10.1093/schbul/sby069

Table 4.

ROC Analyses for a Subset of Questionnaire and Demographic Data

Number of Items Threshold Sensitivity Specificity PPV % NPV % LR+ AUC SE 95% CI P
12 5 0.80 0.57 46 86 1.86 0.73 0.028 0.67–0.78 <.001
11 4 0.84 0.51 45 77 1.71 0.72 0.03 0.65–0.77 <.001
10 4 0.81 0.57 54 77 1.88 0.71 0.028 0.65–0.76 <.001

Note: PPV is the positive predictive—true positive/(true positive+ false positives); NPV is the negative predictive value—true negative/(true negative +false negative). The NPV is very high for all these measures, ie, a negative score really is likely to be negative. The PPV is relatively low (above threshold is 1/3 chance of being a genuine positive).