Abstract
This paper shows that useful designs for variety trials with two replicates, each arranged in a compact array of plots, can be derived from existing row-and-column designs for two non-interacting sets of treatments. Combinatorial and statistical properties are preserved; in particular, if the original design is efficient, then so is the new design.
| Original language | English |
|---|---|
| Pages (from-to) | 645-648 |
| Number of pages | 4 |
| Journal | Journal of the Royal Statistical Society, Series B (Methodological) |
| Volume | 53 |
| Issue number | 3 |
| Publication status | Published - 1991 |
Keywords
- balance
- contraction
- efficiency factor
- nested design
- optimality
- orthogonality
- row-and-column design