We introduce a new approach for creating pointwise confidence intervals for the distribution of event times for current status data. Existing methods are based on asymptotics. Our approach is based on binomial properties and motivates confidence intervals that are very simple to apply and are valid that is guarantee nominal coverage. Although these confidence intervals are necessarily conservative for small sample sizes, asymptotically their coverage rate approaches the nominal one. This binomial approach also motivates approximately valid confidence intervals, and simulations show that these approximate intervals generally have coverage rates closer to the nominal level with shorter length than existing intervals, such as the confidence interval based on the likelihood ratio test. Unlike previous asymptotic methods that require different asymptotic distributions for continuous or grid-based assessment, the binomial approach can be applied to either type of assessment distribution.

中文翻译：

---

当前状态数据的有效和近似有效的置信区间

我们引入了一种新方法来为当前状态数据的事件时间分布创建逐点置信区间。现有的方法是基于渐近的。我们的方法基于二项式属性，并激发了非常易于应用且有效的置信区间，可以保证名义覆盖率。尽管这些置信区间对于小样本量来说必然是保守的，但它们的覆盖率逐渐接近名义上的覆盖率。这种二项式方法还激发了近似有效的置信区间，并且模拟表明，这些近似区间的覆盖率通常更接近名义水平，而长度比现有区间更短，例如基于似然比检验的置信区间。