Optimal designs for comparing several treatments with a control in the presence of explanatory variables
作者:
O. David,
期刊:
Statistics
(Taylor Available online 1994)
卷期:
Volume 25,
issue 4
页码: 325-331
ISSN:0233-1888
年代: 1994
DOI:10.1080/02331889408802456
出版商: Gordon & Breach Science Publishers
关键词: AMS 1980 subject classifications;Primary 62 K 05;secondary 62 K 10;Block designs;control-treatment comparisons;explanatory variables;interaction;linear models;optimal designs
数据来源: Taylor
摘要:
We consider an experiment with blocks of equal size involving some qualitative treatments, one of which is a control treatment, and some controlled explanatory variables that can vary only from one block to another. The assumed model includes interactions between treatments and explanatory variables. The objective of the experiment is to compare the mean responses of the treatments with the mean response of the control for all possible values of the explanatory variables. First, conditions for a design to be optimal are established in the set-up of exact design theory. Then, the construction of designs that satisfy these conditions is studied. Conditions for a design to be optimal under several models are also given. Finally, an example is presented.
点击下载:
PDF (235KB)
返 回