Announcing a new publication for Acta Materia Medica journal. In clinical trials, the primary analysis is often either a test of absolute/relative change in a measured outcome or a corresponding responder analysis. Although each of these tests may be reasonable, determining which test is most suitable for a particular research study remains an open question. These tests may require different sample sizes or define different clinically meaningful differences; most importantly, they may lead to different study conclusions.
The aim of this study was to compare a typical non-inferiority test using absolute change as the study endpoint to the corresponding responder analysis in terms of sample-size requirements, statistical power, and hypothesis-testing results. From numerical analysis, using absolute change as an endpoint generally requires a larger sample size; therefore, when the sample size is the same, the responder analysis has higher power. The cut-off value and non-inferiority margin are critical and can meaningfully affect whether the two types of endpoints yield conflicting conclusions. Specifically, extreme cut-off values are more likely to yield different conclusions. However, this influence decreases as population variance increases. One important reason for conflicting conclusions is a non-normal population distribution.
To eliminate conflicting results, researchers should consider the population distribution and cut-off value selection.
Article Reference: Peijin Wang, Sarah Peskoe and Rebecca Byrd et al. Statistical evaluation of absolute change versus responder analysis in clinical trials. Acta Materia Medica. Vol. 1(3):320-332. DOI: 10.15212/AMM-2022-0020
Keywords: primary endpoints, responder analysis, threshold selection
Acta Materia Medica welcomes the submission of research articles, review articles, databases, mini reviews, commentaries, editorials, short communications, case report articles and study protocols.
Submissions to Acta Materia Medica are made using ScholarOne, the online submission and peer review system. Registration and access are available at https://mc04.manuscriptcentral.com/ammed
Queries about the journal can be sent to firstname.lastname@example.org.
Please visit https://amm-journal.org/ to learn more about the journal.
Editorial Board: https://amm-journal.org/index.php/editorial-board/
There are no author submission or article processing fees.