A Bayesian two-stage group sequential scheme for ordinal endpoints
Journal of the Royal Statistical Society Series C-Applied Statistics
; 2023.
Article
in English
| Web of Science | ID: covidwho-2311850
ABSTRACT
Ordinal endpoints are common in clinical studies. For example, many clinical trials for evaluating COVID-19 infection therapies have adopted an ordinal scale as recommended by the World Health Organization. Despite their importance in clinical studies, design methods for ordinal endpoints are limited;in practice, a dichotomized approach is often used for simplicity. Here, we introduce a Bayesian group sequential scheme to assess ordinal endpoints, which considers a proportional-odds (PO) model, a nonproportional-odds (NPO) model, and a PO/NPO-switch model to handle various scenarios. Extensive simulations are conducted to demonstrate desirable performance, and the R package BayesOrdDesign has been made publicly available.
Full text:
Available
Collection:
Databases of international organizations
Database:
Web of Science
Language:
English
Journal:
Journal of the Royal Statistical Society Series C-Applied Statistics
Year:
2023
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS