TREATING BIAS AS VARIANCE FOR EXPERIMENTAL-DESIGN PURPOSES

被引：18

作者：

DRAPER, NR

GUTTMAN, I

机构：

[1] UNIV WISCONSIN,DEPT STAT,1210 W DAYTON ST,MADISON,WI 53706

[2] UNIV TORONTO,DEPT STAT,TORONTO M5S 1A1,ONTARIO,CANADA

来源：

ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS | 1992年 / 44卷 / 04期

关键词：

BIAS ERROR; EXPERIMENTAL DESIGN; RESPONSE SURFACE; VARIANCE ERROR;

D O I：

10.1007/BF00053396

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：

When an empirical model is fitted to data, bias can arise from terms that have not been incorporated, and this can have an important effect on the choice of an experimental design. Here, the biases are treated as random, and the consequences of this action are explored for the fitting of models of first and second order.

引用

页码：659 / 671

页数：13

共 12 条

[1]

Bandemer H., 1987, STATISTICS, V18, P171

[2]

BOX GEP, 1959, J AM STAT ASSOC, V54, P622

[3]

BOX GEP, 1963, BIOMETRIKA, V50, P335, DOI 10.1093/biomet/50.3-4.335

[4]

BUNKE H, 1986, STATISTICAL INFERENC