Measurement Precision with Ordinal Categorical Data considering Dose-response Relationships

Abstract

: Evaluating measurement methods is important to perform quality assurance of measurement results. This study aims to estimate the measurement precision of ordinal categorical data. ISO 5725-1 states that precision of measurement methods can be quantified by conducting precision evaluation experiments, and ISO 5725-2 provides a methodology to evaluate the measurement precision for quantitative data. Regarding qualitative data, some previous studies exist on quantifying the precision of binary and multinomial data. However, no reasonable methodologies have yet been established. Thus, this study proposes the analysis method for the data obtained from a collaborative study on intratracheal administration testing for assessing effects in rat lungs. A primary objective of the collaborative study was to demonstrate dose-response relationships. To investigate the dose-response relationships, hypothesis tests such as a Cochran–Armitage trend test and a cumulative chi-squared test were performed, which are applicable even for ordinal categorical data. Moreover, logistic regression analysis was performed to examine the dose-response relationships and the precision among laboratories. This result was expressed by 50% efficient dose ( 𝐸𝐸𝐸𝐸 50 ) and area under the curve (AUC). Then, we obtained that a dose-response relationship was observed for each laboratory, and the differences in the relationships among laboratories expressed precision.