随机左截断数据下条件分位数的光滑经验似然推断

Smoothed empirical likelihood confidence intervals for conditional quantiles under randomly left-truncated data

应用光滑的经验似然方法来构造随机左截断数据下条件分位数的置信区间.在一定的条件下,证明了经验似然比统计量渐近服从自由度为1的卡方分布.模拟数据表明,在构造条件分位数的置信区间时,经验似然方法比正态逼近方法效果更好.

In this paper, we employ the method of smoothed empirical likelihood to construct confi- dence intervals for the conditional quantile under randomly left - truncated data. It is proved that the empirical likelihood ratio statistic is asymptotically chi - square distributed with one degree of freedom under some mild conditions. The simulation results show that the method of empirical likelihood per- forms better than the normal -approximfion -based method when we construct confidence intervals of the conditional quantile.