Challenge Your Exam Readiness With Our Free EPPP Practice Questions

Predictive values depend on disease prevalence. With sensitivity and specificity held constant, positive predictive value (PPV)—the probability that someone who tests positive actually has the condition—increases as prevalence rises, because true positives become a larger proportion of all positives. Conversely, in low-prevalence settings, even a highly specific test yields more false positives relative to true positives, reducing PPV. Negative predictive value (NPV) shows the opposite pattern, tending to decrease as prevalence increases because false negatives form a larger slice of all negatives. Sensitivity (true-positive rate) and specificity (true-negative rate) are properties of the test itself and are unaffected by prevalence, but predictive values are properties of the test in a population context. Bayes’ theorem formalizes these relationships by weighting the likelihood ratio of the test with the pretest probability (base rate). Understanding these dynamics is critical for clinical decision-making, referral thresholds, and public health screening strategies, and is a frequent EPPP topic linking statistical reasoning to evidence-based practice.