explanation. The calculation of the sample size during the development of a diagnostic precision study allows for sufficient precision. The calculation of sample size also takes into account the specific objectives and assumptions of the study. Very often, contract studies are an indirect attempt to validate a new system or evaluation instrument. In other words, in the absence of a final criterion variable or a „gold standard,“ the accuracy of a scale or instrument is assessed by comparing its results when used by different advisors. Here, we can use methods that address the problem of real anxiety – to what extent do ratings reflect the true property we want to measure? Sensitivity and specificity are fundamental performance criteria for a diagnostic test. Together, they describe the extent to which a test can determine whether a given condition is present or non-existent. The FDA recommends that you communicate measurements of diagnostic accuracy (pairs of sensitivities and specificities, pairs of positive and negative probabilities) or measures of agreement (percent positive consent and percentage of negative consent) and their 95 percent confidence intervals. We recommend that these indicators be both groups (z.B 490/500) and percentages (z.B 98.0%) report. The appendices have a numerical example.

Valenstein, P. (1990). Evaluation of diagnostic tests with imperfect standards. American Journal of Clinical Pathology, 93, 252-258. A priority specification of study hypotheses limits the chances of dredging post-hoc data with misleading results, premature conclusions on conducting tests or subjective evaluations of test accuracy. Goals and assumptions also guide sample size calculations. 22 There is little consensus on the most appropriate statistical methods for analyzing the agreement of rating agencies (we will use the generic terms „squors“ and „ratings“ to include observers, judges, diagnostic tests, etc.