作者: Ralph S. Woodruff
DOI: 10.1080/01621459.1971.10482279
关键词: Mathematics 、 Taylor series 、 Expression (mathematics) 、 Simple (abstract algebra) 、 Random variable 、 Mathematical optimization 、 Type (model theory) 、 Applied mathematics 、 Linear form 、 Sample (statistics) 、 Variance (accounting)
摘要: Abstract A method often used for computing the variance of a complicated sample estimate is to first apply Taylor approximation reduce non-linear forms variables linear form. This article shows useful results which can be obtained by merely reversing order between selection units and component in this expression. The completely general (assuming that samples are large enough justify using approximation) involving no restrictions on (a) form estimate, (b) number random involved (c) type, complexity or designs estimate.