Random and systematic arrangements
成果类型：
Article
署名作者：
Jeffreys, H
刊物名称：
BIOMETRIKA
ISSN/ISSBN：
0006-3444
发表日期：
1939
页码：
18
关键词：
摘要：
A distinction is drawn between randomness in the design of expts. and randomness in the sense of mutual irrelevance of the errors. The latter is what is needed for the validity of most statistical methods, and is not necessarily improved by the former. Examples are given from various subjects. The author agrees in general with Fisher''s recommendation to estimate and eliminate known effects as accurately as possible and randomize the rest.