A multi-treatment two stage allocation design for survival outcomes with nonrandom censoring: a copula-based approach

• Published in: Sequential analysis Vol. 43; no. 4; pp. 461 - 476
• Main Authors: Das, Soumyadeep, Bhattacharya, Rahul, Shome, Madhumita
• Format: Journal Article
• Language: English
• Published: Philadelphia Taylor & Francis 01.10.2024; Taylor & Francis Ltd
• Subjects: Asymptotic methods; Asymptotic p-value; Clayton copula; nonrandom censoring; Randomization; Statistical tests; Survival; Survival analysis; survival trials; two-stage adaptive design
• ISSN: 0747-4946; 1532-4176
• DOI: 10.1080/07474946.2024.2418578

In the context of clinical trials, a multi-treatment two-stage adaptive randomization procedure is developed for survival responses with copula-based nonrandom censoring. Because no such allocation design is available for survival responses with nonrandom censoring, this is probably the first work in this direction. After allocating the first-stage patients by complete randomization (CR), asymptotic p-values of relevant statistical tests are used to derive the allocation probabilities for the second-stage incoming patients. Several design and precision-based operating characteristics of the proposed design are studied both theoretically and empirically and compared with those of the CR procedure and the two-stage design of Bhattacharya and Shome (2019). Applicability of the proposed design is further envisaged through redesigning a real clinical trial with cancer patients.