This article proposes methods for constructing balanced semi-latin rectangles, indicating new designs for agricultural experiments.
AbstractSemi-Latin rectangles (SLR) are row-column designs where each intersection contains the same number of experimental units, denoted as k >1. Moreover, each treatment appears an equal number of times in each row (nr, say) and in each column (nc, say) (nr > 1 and nc > 1 may or may not be equal). Balanced Semi-Latin rectangles (BSLR) form a subset of SLR, extending the concepts of Latin squares and Semi-Latin squares (SLS). These designs are applicable in various agricultural and industrial experiments, particularly in scenarios where one effect is considered a column effect and the other a row effect, with each intersection accommodating exactly 3 units. This article proposed two methods for constructing BSLR designs with a block size of 3. Additionally, an R package has been developed for generating these designs.
No takes yet. Share an insight, caveat, or question.
Yadav et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: