Lesaffre Emmanuel
Department of Biostatistics, Erasmus MC, Rotterdam, The Netherlands.
Bull NYU Hosp Jt Dis. 2012;70(2):65-72.
In a follow-up study, patients are monitored over time. Longitudinal and time-to-event studies are the two most important types of a follow-up study. In this paper, the focus is on longitudinal studies with a continuous response where patients are examined at several time points. While longitudinal studies provide a powerful tool for the evaluation of a treatment effect over time, a major problem is missing data caused, for example, by patients who drop out from the study. Many longitudinal studies in rheumatology use inappropriate statistical methodology because either they do not address correctly the correlated nature of the repeated measurements, or they treat the problem of missing data incorrectly. We will illustrate that there are interpretational and computational issues with the "classical" approaches. Further, we expand here on more appropriate statistical techniques to analyze longitudinal studies. To this end, we focus on randomized controlled trials (RCTs) and illustrate the approaches on data from a fictive randomized controlled trial in rheumatology.
在一项随访研究中，会对患者进行长期监测。纵向研究和事件发生时间研究是随访研究的两种最重要类型。在本文中，重点是具有连续反应的纵向研究，在多个时间点对患者进行检查。虽然纵向研究为评估一段时间内的治疗效果提供了一个强大的工具，但一个主要问题是数据缺失，例如由退出研究的患者导致的数据缺失。许多风湿病学的纵向研究使用了不恰当的统计方法，因为要么它们没有正确处理重复测量的相关性，要么它们错误地处理了数据缺失问题。我们将说明“经典”方法存在解释和计算方面的问题。此外，我们在此扩展更合适的统计技术来分析纵向研究。为此，我们专注于随机对照试验（RCT），并以风湿病学中一个虚构的随机对照试验的数据来说明这些方法。
