arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.11583stat.MEstat.APstat.ML
收藏

非正态模型的容差和预测区间

Tolerance and Prediction Intervals for Non-normal Models

Geoffrey S Johnson

摘要:

预测区间涵盖了重复采样中随机过程的未来观测值,通常通过确定一个关键量来构建,该关键量也是一个从属统计量。类似地,容许区间涵盖重复抽样中的总体百分位数,并且通常基于关键量。我们在非正态模型中考虑的一种方法利用了一个链接函数,该链接函数导致近似正态分布的关键量。在这种正态近似不成立的情况下,我们考虑基于平均值的置信区间进行公差和预测的第二种方法。这些方法直观、易于实现、具有适当的操作特性,并且与贝叶斯、重新采样和机器学习方法相比在计算上是高效的。这一点在多中心临床试验招募的背景下得到了证明,其中临床试验中心启动时间错开,实际治疗时间和临床终点的研究结束成功。

英文摘要:

A prediction interval covers a future observation from a random process in repeated sampling, and is typically constructed by identifying a pivotal quantity that is also an ancillary statistic. Analogously, a tolerance interval covers a population percentile in repeated sampling and is often based on a pivotal quantity. One approach we consider in non-normal models leverages a link function resulting in a pivotal quantity that is approximately normally distributed. In settings where this normal approximation does not hold we consider a second approach for tolerance and prediction based on a confidence interval for the mean. These methods are intuitive, simple to implement, have proper operating characteristics, and are computationally efficient compared to Bayesian, re-sampling, and machine learning methods. This is demonstrated in the context of multi-site clinical trial recruitment with staggered site initiation, real-world time on treatment, and end-of-study success for a clinical endpoint.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑