Langton S D, Chevennement R, Nagelkerke N, Lombard B
DEFRA Central Science Laboratory, Sand Hutton, York, UK.
Int J Food Microbiol. 2002 Dec 15;79(3):175-81. doi: 10.1016/s0168-1605(02)00107-1.
In qualitative (detection) food microbiology, the usual measures of repeatability and reproducibility are inapplicable. For such studies, we introduce two new measures: accordance for within laboratory agreement and concordance for between laboratory agreement, and discuss their properties. These measures are based on the probability of finding the same test results for identical test materials within and between laboratories, respectively. The concordance odds ratio is introduced to present their relationship. A method to test whether accordance differs from concordance is discussed.
在定性（检测）食品微生物学中，通常的重复性和再现性测量方法并不适用。对于此类研究，我们引入了两种新的测量方法：用于实验室内部一致性的符合度和用于实验室间一致性的一致性，并讨论了它们的特性。这些测量方法分别基于在实验室内部和实验室之间对相同测试材料获得相同测试结果的概率。引入一致性比值比来表示它们之间的关系。还讨论了一种检验符合度是否不同于一致性的方法。
