A fast algorithm for balanced sampling

被引：41

作者：

Chauvet, G

Tillé, Y

机构：

[1] ENSAI, CREST, Lab Stat Enquete, F-35170 Bruz, France

[2] Univ Neuchatel, Stat Grp, CH-2002 Neuchtel, Switzerland

来源：

COMPUTATIONAL STATISTICS | 2006年 / 21卷 / 01期

关键词：

algorithm of balanced sampling; auxiliary variables; balanced sampling; sampling design; unequal probabilities sampling;

D O I：

10.1007/s00180-006-0250-2

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

The cube method (Deville & Tillw 2004) is a large family of algorithms that allows selecting balanced samples with equal or unequal inclusion probabilities. In this paper, we propose a very fast implementation of the cube method. The execution time does not depend on the square of the population size anymore, but only on the population size. Balanced samples can thus be selected in very large populations of several hundreds of thousands of units.

引用

页码：53 / 62

页数：10

共 8 条

[1]

[Anonymous], 2001, THEORIE SONDAGES ECH

[2]

[Anonymous], J STAT PLANNING INFE

[3]

BERTRAND P, 2004, IN PRESS SERIES INSE

[4] Efficient balanced sampling:: The cube method [J].