Which statement best describes the relationship among sensitivity, accuracy, and specificity?

Which statement best describes the relationship among sensitivity, accuracy, and specificity?

• A. Sensitivity > Accuracy > Specificity
• B. Accuracy lies between sensitivity and specificity
• C. Specificity > Accuracy > Sensitivity
• D. NPV > PPV

Answer: (B)

Accuracy represents the overall proportion of correct classifications, combining true positives and true negatives. Sensitivity and specificity describe how well the test identifies diseased and non-diseased individuals, respectively, independent of how common the disease is. The key relationship is that accuracy is a prevalence-weighted average of sensitivity and specificity: accuracy = prevalence × sensitivity + (1 − prevalence) × specificity. Since prevalence ranges from 0 to 1, this weighted average must fall between sensitivity and specificity. If the disease is very common, accuracy leans toward sensitivity; if it’s rare, accuracy leans toward specificity. Predictive values (NPV and PPV) are not the metric describing this relationship, as they depend on prevalence in a different way.

Accuracy represents the overall proportion of correct classifications, combining true positives and true negatives. Sensitivity and specificity describe how well the test identifies diseased and non-diseased individuals, respectively, independent of how common the disease is. The key relationship is that accuracy is a prevalence-weighted average of sensitivity and specificity: accuracy = prevalence × sensitivity + (1 − prevalence) × specificity. Since prevalence ranges from 0 to 1, this weighted average must fall between sensitivity and specificity. If the disease is very common, accuracy leans toward sensitivity; if it’s rare, accuracy leans toward specificity. Predictive values (NPV and PPV) are not the metric describing this relationship, as they depend on prevalence in a different way.