Optimal block designs comparing treatments with a control when the errors are correlated |
| |
Authors: | J Kunert RJ Martin J Eccleston |
| |
Institution: | 1. Department of Statistics, TU Dortmund University, 44221 Dortmund, Germany;2. Wirksworth DE4 4EB, UK;3. Department of Mathematics, University of Queensland, Brisbane, Qld 4072, Australia |
| |
Abstract: | The efficient design of experiments for comparing a control with v new treatments when the data are dependent is investigated. We concentrate on generalized least-squares estimation for a known covariance structure. We consider block sizes k equal to 3 or 4 and approximate designs. This method may lead to exact optimal designs for some v, b, k, but usually will only indicate the structure of an efficient design for any particular v, b, k, and yield an efficiency bound, usually unattainable. The bound and the structure can then be used to investigate efficient finite designs. |
| |
Keywords: | Efficient design Correlated errors Optimal design Supplemented balance |
本文献已被 ScienceDirect 等数据库收录! |
|