In large epidemiologic studies, self-reported outcomes are often used to record disease status more frequently than by gold standard diagnostic tests alone. While self-reported disease outcomes are easier to obtain than diagnostic test results, they are often prone to error. There has recently been interest in using error-prone, auxiliary outcomes to improve the efficiency of inference for discrete time-to-event analyses. We have developed a new augmented likelihood approach that incorporates auxiliary data into the analysis of gold standard time-to-event outcome, which can be considered when self-reported outcomes are available in addition to a gold standard endpoint. We conduct a numerical study to show how we can improve statistical efficiency by using the proposed method instead of standard approaches for interval-censored survival data that do not leverage auxiliary data. We also extended this method for the complex survey design setting so that it can be applied in our motivating data example. We apply this method to data from the Hispanic Community Health Study/Study of Latinos in order to assess the association between energy and protein intake and the risk of incident diabetes. In our application, we demonstrate how our method can be used in combination with regression calibration to additionally address the covariate measurement error in the self-reported diet.
翻译:在大型的流行病学研究中,自我报告的结果往往被用来记录疾病状况,而不是仅仅通过黄金标准诊断检测结果。虽然自我报告的结果比诊断测试结果更容易获得,但往往容易出错。最近人们有兴趣使用容易出错的辅助结果,以提高独立时间到活动分析的推断效率。我们开发了一种新的增强可能性的方法,将辅助数据纳入黄金标准时间到活动结果的分析,在除黄金标准端点外,提供自我报告的结果时,可以考虑这些数据。我们进行了一项数字研究,以表明我们如何能够通过使用拟议方法而不是不利用辅助数据的定期检查生存数据标准方法来提高统计效率。我们还扩展了复杂的调查设计设置方法,以便用于我们的激励数据实例。我们将这种方法应用于拉美裔社区健康研究/拉丁美洲人研究的数据,以便评估能源和蛋白摄入与事件糖尿病风险之间的联系。我们的应用中,我们展示了我们的方法如何通过采用自我分析的自我测量与进一步校准的自我测量方法。