On the optimality of the generalized room squares (Q3313154)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 3843019
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | On the optimality of the generalized room squares |
scientific article; zbMATH DE number 3843019 |
Statements
On the optimality of the generalized room squares (English)
0 references
1983
0 references
generalized Room squares
0 references
sub-plot analysis
0 references
main-plot analysis
0 references
balanced incomplete block design
0 references
parametric contrasts
0 references
incidence matrix
0 references
universal optimality
0 references
0.7740772366523743
0 references
0.7722889184951782
0 references
0.7661247253417969
0 references
0.7579975128173828
0 references
The optimality of a special class of incomplete block designs, namely generalised room square (GRS) designs, has been considered in this paper. Let D denote a class of Room square designs which satisfy the conditions: (a) each cell is either empty or contains k symbols, (b) every row (column) contains each symbol precisely once, (c) each pair of symbols occurs \(\lambda\) times in a cell. A design \(d\in D\) having the model proposed by \textit{J. W. Archbold} and \textit{N. L. Johnson} [Ann. Math. Stat. 29, 219-225 (1958; Zbl 0085.009)] is used and if it satisfies the condition 'c' it is optimal in D. Further, a theorem is proved that if a design belonging to D is a GRS, it is universally optimal in respect of the estimation of the treatment effects. Another theorem as a special case of the first theorem has also been proved. The authors have not exemplified any real problem in giving the layout and its analysis. References are adequate.
0 references