发表机构
University of Tsukuba; Astellas Pharma Global Development Inc.; Wakayama Medical University; UCB Japan Co., Ltd.（筑波大学; 安斯泰来全球开发公司; 和歌山医科大学; UCB日本有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究证明在非随机缺失机制下，MMRM检验在全局零假设下仍有效，提出比例观测条件，并通过模拟验证，表明无需过度保守的检验程序。
AI 中文摘要
在具有纵向连续结局的随机临床试验中，非随机缺失（MNAR）的缺失机制常常促使研究者采用比混合效应模型重复测量（MMRM）更为保守的替代方法。这种谨慎对于估计而言是重要的，但估计和检验并不需要相同的假设。此外，过度保守的主要分析可能会降低检验效能，增加所需样本量，并提高试验成本。我们研究了在跨组纵向结局分布相同的全局零假设下，基于MMRM的检验的有效性。由于有效的检验在零假设下至少要求处理效应估计量收敛到零，我们研究了这一性质的充分条件。我们引入了一个比例观测条件，该条件要求相对于参考组的观测概率之比，在给定完整结局向量的条件下，与结局无关，并证明了在任意基线后访视和单调缺失的情况下，该条件是收敛到零值的充分条件。该条件允许观测依赖于未观测到的结局，并允许通过结局无关的脱落来体现组间总体观测概率的差异，使其具有临床可解释性，同时容纳结局依赖的MNAR缺失。合成和基于数据的自举模拟显示偏差可忽略不计，经验检验规模接近0.05，包括非单调缺失情况。因此，MNAR缺失本身并不必然意味着需要更保守的主要检验程序。这一结果并不为备择假设下的处理效应估计提供依据，后者仍需要基于估计目标的解释和敏感性分析。
英文摘要
In randomized clinical trials with longitudinal continuous outcomes, missing-not-at-random (MNAR) missingness often motivates conservative alternatives to mixed models for repeated measures (MMRM). Such caution is important for estimation, but estimation and testing need not require identical assumptions. Moreover, overly conservative primary analyses may reduce power, increase required sample size, and raise trial costs. We investigated the validity of MMRM-based testing under the global null of identical longitudinal outcome distributions across groups. Because valid testing minimally requires treatment-effect estimators to converge to the null under the null hypothesis, we investigated sufficient conditions for this property. We introduced a proportional observation condition requiring ratios of observation probabilities relative to a reference group, conditional on the full outcome vector, to be outcome-independent, and showed that, with arbitrary post-baseline visits and monotone missingness, this condition is sufficient for convergence to the null value. The condition allows observation to depend on unobserved outcomes and permits between-group differences in overall observation probabilities through outcome-independent dropout, making it clinically interpretable while accommodating outcome-dependent MNAR missingness. Synthetic and data-based bootstrap simulations showed negligible bias and empirical test sizes near 0.05, including nonmonotone missingness. Thus, MNAR missingness does not by itself imply that a more conservative primary testing procedure is required. This result does not justify treatment-effect estimation under alternatives, which still requires estimand-based interpretation and sensitivity analyses.
