This function calculate the performance, based on Bayes theorem, of a
svmpartest(X)
X=[80 3; 5 20]; svmpartest(X) Answer is: Prevalence: 78.7% Sensitivity (probability that test is positive on unhealthy subject): 94.1% 95% confidence interval: 89.1% - 99.1% False negative proportion: 5.9% Specificity (probability that test is negative on healthy subject): 87.0% 95% confidence interval: 73.2% - 100.0% False positive proportion: 13.0% Youden's Index (a perfect test would have a Youden index of +1): 0.8107 Accuracy or Potency: 92.6% Mis-classification Rate: 7.4% Predictivity of positive test (probability that a subject is unhealthy when test is positive): 96.4% 95% confidence interval: 92.4% - 100.0% Positive Likelihood Ratio: 7.2 Moderate increase in possibility of disease presence Predictivity of negative test (probability that a subject is healthy when test is negative): 80.0% 95% confidence interval: 64.3% - 95.7% Negative Likelihood Ratio: 0.1 Large (often conclusive) increase in possibility of disease absence Error odds ratio: 2.4000 Diagnostic odds ratio: 106.6667 Discriminant Power: 2.6 A test with a discriminant value of 1 is not effective in discriminating between affected and unaffected individuals. A test with a discriminant value of 3 is effective in discriminating between affected and unaffected individuals. Test bias: 0.9765 Test underestimates the phenomenon Number needed to Diagnose (NDD): 1.2 Created by Giuseppe Cardillo giuseppe.cardillo-edta@poste.it To cite this file, this would be an appropriate format: Cardillo G. (2006). Clinical test performance: the performance of a clinical test based on the Bayes theorem. http://www.mathworks.com/matlabcentral/fileexchange/12705