Abstract
Three research problems, for which there was no obvious textbook design available, are presented. Each of the three involve constructing incomplete block designs for factorial treatment arrangements. While the designs are not likely optimal by any of the classical criteria, they meet the objectives of the research projects. The constructions involved confounding, with incomplete blocks, those effects which were of least interest. However, effects of interest were also allowed to be slightly non-orthogonal to blocks in order to be able to examine a larger number of effects of interest.
Keywords
Incomplete blocks, factorial designs, confounding, row-column designs, non-orthogonal designs
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Recommended Citation
Allen, O. B. and Ryan, D. A.J.
(1994).
"DESIGN FOR THE EXPERIMENTER,"
Conference on Applied Statistics in Agriculture.
https://doi.org/10.4148/2475-7772.1357
DESIGN FOR THE EXPERIMENTER
Three research problems, for which there was no obvious textbook design available, are presented. Each of the three involve constructing incomplete block designs for factorial treatment arrangements. While the designs are not likely optimal by any of the classical criteria, they meet the objectives of the research projects. The constructions involved confounding, with incomplete blocks, those effects which were of least interest. However, effects of interest were also allowed to be slightly non-orthogonal to blocks in order to be able to examine a larger number of effects of interest.
