×

Construction of balanced semi-Latin rectangles in block size four: an algorithmic approach. (English) Zbl 07889740

Summary: Semi-Latin rectangles are row-column designs in which each row-column intersection has same number of experimental units, say \(k > 1\) and each treatment appears same number of times in each row and same number of times in each column. Balanced Semi-Latin rectangles (BSLR) are the subclass of Semi-Latin rectangles (SLR) which are generalizations of Latin squares and Semi-Latin squares (SLS). Such types of designs are more useful in various agricultural as well as industrial experiments in which one of the effects can be consider as column effect and another as row effect, where the intersection of effects can only accommodate 4 units. This article proposes an algorithm to construct BSLR designs with a block size of four.

MSC:

62K10 Statistical block designs
05B15 Orthogonal arrays, Latin squares, Room squares
62K05 Optimal statistical designs
Full Text: DOI

References:

[1] Bailey, RA, Semi-Latin squares, J Stat Plan Inference, 18, 3, 299-312, 1988 · Zbl 0639.62066 · doi:10.1016/0378-3758(88)90107-3
[2] Bailey, RA, Efficient semi-Latin squares, Stat Sin, 2, 413-437, 1992 · Zbl 0822.62060
[3] Bailey, RA; Chigbu, PE, Enumeration of semi-Latin squares, Discrete Math, 167, 73-84, 1997 · Zbl 0901.05017 · doi:10.1016/S0012-365X(96)00217-8
[4] Bailey, RA; Monod, H., Efficient semi-Latin rectangles: designs for plant disease experiments, Scand J Stat, 28, 2, 257-270, 2001 · doi:10.1111/1467-9469.00235
[5] Bailey, RA; Royle, G., Optimal Semi-Latin squares with side six and block size two, Proc R Soc Lond Ser A Math Phys Eng Sci, 453, 19, 1903-1914, 1997 · Zbl 0935.62087 · doi:10.1098/rspa.1997.0102
[6] Bailey, RA; Soicher, LH, Uniform semi-Latin squares and their pairwise-variance aberrations, J Stat Plan Inference, 213, 282-291, 2021 · Zbl 1460.62121 · doi:10.1016/j.jspi.2020.12.003
[7] Bedford, D.; Whitaker, RM, A new construction for efficient Semi-Latin squares, J Stat Plan Inference, 98, 1-2, 287-292, 2001 · Zbl 0977.62083 · doi:10.1016/S0378-3758(00)00303-7
[8] Chigbu, PE, The“ Best” of the three optimal (4× 4)/4 semi-Latin squares, Sankhya Indian J Stat, 65, 3, 641-648, 2003 · Zbl 1193.62141
[9] Choi, KC; Gupta, S., Confounded row-column designs, J Stat Plan Inference, 138, 196-202, 2008 · Zbl 1144.62333 · doi:10.1016/j.jspi.2007.05.012
[10] Godolphin, JD, Construction of row-column factorial designs, J R Stat Soc Ser B, 81, 335-360, 2019 · Zbl 1420.62337 · doi:10.1111/rssb.12305
[11] John, JA, Bounds for the efficiency factor of row-column designs, Biometrika, 79, 3, 658-661, 1992 · Zbl 0775.62209 · doi:10.1093/biomet/79.3.658
[12] Parsad, R., A note on semi-Latin squares, J Indian Soc Agric Stat, 60, 2, 131-133, 2006 · Zbl 1188.05041
[13] Price, WC, Measurement of virus activity in plants, Biometrics Bull, 2, 5, 81-86, 1946 · doi:10.2307/3001982
[14] Soicher, LH, Uniform semi-Latin squares and their Schur-optimality, J Combin Designs, 20, 6, 265-277, 2012 · Zbl 1248.05022 · doi:10.1002/jcd.21300
[15] Soicher, LH, Optimal and efficient semi-Latin squares, J Stat Plan Inference, 143, 3, 573-582, 2013 · Zbl 1428.62358 · doi:10.1016/j.jspi.2012.08.010
[16] Uto, NP; Bailey, RA, Balanced Semi-Latin rectangles: properties, existence and constructions for block size two, J Stat Theory Pract, 14, 3, 1-11, 2020 · Zbl 1456.62162 · doi:10.1007/s42519-020-00118-3
[17] Uto, NP; Bailey, RA, Constructions for regular-graph Semi-Latin rectangles with block size two, J Stat Plan Inference, 221, 81-89, 2022 · Zbl 1491.62078 · doi:10.1016/j.jspi.2022.02.007
[18] Wang, PC, Orthogonal main-effect plans in row-column designs for two-level factorial experiments, Commun Stat Theory Methods, 46, 10685-10691, 2017 · Zbl 1453.62609 · doi:10.1080/03610926.2016.1242743
[19] Youden, WJ, Dilution curve of tobacco-mosaic virus, Contrib Boyce Thompson Inst, 9, 49-58, 1937
[20] Zhou, Z.; Zhou, YD, Optimal row-column designs, Biometrika, 110, 537-549, 2023 · Zbl 07689571 · doi:10.1093/biomet/asac046
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.