Cole S R
Division of Preventive Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA 02215, USA.
Comput Methods Programs Biomed. 1999 Jul;60(1):79-82. doi: 10.1016/s0169-2607(99)00016-4.
Nonparametric bootstrap statistical inference is a robust computer intensive method for generating estimates of statistical variability for which formulae are not known or asymptotic assumptions are not met. A SAS macro that implements simple nonparametric bootstrap statistical inference is presented with an example. The program code is easily generalized to any SAS procedure which includes a BY statement, and to cases of clustered data.
非参数自助法统计推断是一种强大的计算机密集型方法，用于生成统计变异性的估计值，这类估计值的公式未知或不满足渐近假设。本文通过一个示例展示了一个实现简单非参数自助法统计推断的SAS宏。该程序代码可以很容易地推广到任何包含BY语句的SAS过程以及聚类数据的情况。
