"TAGS", a programme for the evaluation of test ...
|Title||"TAGS", a programme for the evaluation of test accuracy in the absence of a gold standard|
|Author(s)||R. Pouillot, G. Gerbier, I. Gardner|
|Journal||Preventive Veterinary Medicine|
|Abstract||When a perfect reference test (i.e. "gold standard") is not available, it is possible to obtain estimates of test sensitivity and specificity using "latent-class" methods. However, there are few widely available software programmes that allow the implementation of these procedures. The following article describes the development of a programme (implemented in R and S-Plus software) for this purpose that yields maximum-likelihood estimates of sensitivity, specificity and prevalence. An HTML form, which submits data to a web-based interface to R, has also been implemented. The programmes can incorporate data obtained from several populations, results of multiple tests, and can account for data obtained from a reference population in which the true status (infected or non-infected) of each individual is specifically known. Two estimation methods are used: a Newton-Raphson procedure and an expectation-maximization (EM) procedure. The estimation methods assume test independence conditional on the infection status of the individuals and constant test accuracy in each population. A goodness-of-fit statistic and the residuals of pairwise correlation coefficients are calculated to check the validity of these assumptions. Two examples are used to illustrate the application and limitations of the programmes. The programmes are available at www.afssa.fr/interne/tags.htm (Europe) or www.epi.ucdavis.edu/diagnostictests/ (USA).|
Using APA 6th Edition citation style.
Times viewed: 55