Improved Nonparametric Bootstrap Tests of Lorenz Dominance
提出基于接触集初步估计的新非参数自助检验方法，用于判断一个收入或财富分布是否洛伦兹占优于另一个，在相关样本量下比现有方法具有更高检验功效。
One income or wealth distribution is said to Lorenz dominate another when the Lorenz curve for the former is nowhere below that of the latter, indicating a (weakly) more equitable allocation of resources. Existing tests of the null of Lorenz dominance based on pairs of samples of income or wealth achieve the nominal rejection rate asymptotically when the two Lorenz curves are equal, but are conservative at other null configurations. We propose new nonparametric bootstrap tests of Lorenz dominance based on preliminary estimation of a contact set. Our tests achieve the nominal rejection rate asymptotically on the boundary of the null; that is, when Lorenz dominance is satisfied, and the Lorenz curves coincide on some interval. Numerical simulations indicate that our tests enjoy substantially improved power compared to existing procedures at relevant sample sizes. Supplementary materials for this article are available online.