This utility can be used to compare the performance of two tests evaluated in the same population.
Kappa and proportions of positive and negative agreement are calculated, as well as McNemar's Chi-squared value. Corresponding p-values
are also calculated for both kappa and Chi-squared values. For infected populations, sensitivity values are
calculated for both tests, as well as sensitivity covariances.
Similarly, if the population is specified as uninfected, specificity values and specificity covariances are calculated,
including Wilson binomial confidence limits for Se and sp estimates.
- Fleiss JL, 1981. Statistical methods for rates and proportions,
2nd Ed. John Wiley and Sons, New York. Chapter 13.
- Cicchetti DV, Feinstein AR, 1990. High agreement but low kappa: II. Resolving the paradoxes. J. Clin. Epidemiol. 43: 551-558,
for details of kappa(pos) and kappa(neg); and
- Gardner IA, Stryhn H, Lind P, Collins MT, 2000. Conditional dependence between tests
affects the diagnosis and surveillance of animal diseases. Prev. Vet. Med. 45: 107-122 for calculation and application of test covariances.