含零总体中位数的经验似然

当所研究的总体中含有一定比率的零值,而其余的值大于零时,则称为含零总体。文章利用Owen的经验似然方法来构造这类总体的中位数的置信区间,所得结果不需要假设总体服从某种参数模型,并能利用样本中零值的信息,而且构造的置信区间受非零总体偏斜的影响比一些其他非参数方法小一些。同时,随机模拟的结果也显示了这一点。

Empirical Likelihood-based Confidence Intervals for Medium of Population with Zero Values

A population in which a substantial number of observations takes zero value and at the same time the non-zero observations are positive and highly skewed is called population with zero values. Empirical likelihood-based nonparametric confidence intervals for the medium parameter of the population are proposed in this paper, which have two unique features. One is that no parametric model is needed for assumption and the information contained in the zero observations is fully utilized. The other is that the confidence intervals are more reflective to the skewness in the non-zero observations than those based on other non-parametric methods for median confidence intervals.