A variety trial sometimes requires a resolvable block design in which the replicates are set out next to each other. The long blocks running through the replicates are then of interest. A t-latinized design is one in which groups of these t long blocks are binary. In this paper examples of such designs are given. It is shown that the algorithm described by John & Whitaker (1993) can be used to construct designs with high average efficiency factors. Upper bounds on these efficiency factors are also derived.

SUMMARY The construction of optimal or nearly optimal block designs, using the A-optimality criterion, is formulated as a non-linear 0–1 programme. An approach which ignores the 0–1 constraint is suggested and its feasibility is examined by constructing block designs using the non-linear programming computer package MINOS.

SummaryA method is given for constructing row and column designs for situations where replicates are contiguous. Designs of this type are needed in cotton variety trials. A table of generating arrays is given from which a series of resolvable designs can be constructed; these designs are called latinized α‐designs. Some results from cotton variety trials are presented.

Journal Article Row-column α-designs Get access J. A. JOHN, J. A. JOHN Department of Mathematics, University of SouthamptonSouthampton S09 5NH, U.K. Search for other works by this author on: Oxford Academic Google Scholar J. A. ECCLESTON J. A. ECCLESTON Department of Statistics, University of New South WalesKensington 2033, Australia Search for other works by this author on: Oxford Academic Google Scholar Biometrika, Volume 73, Issue 2, August 1986, Pages 301–306, https://doi.org/10.1093/biomet/73.2.301 Published: 01 August 1986 Article history Received: 01 July 1985 Revision received: 01 October 1985 Published: 01 August 1986

SUMMARY The analysis of row‐column designs which satisfy the property of adjusted orthogonality is considered. For such designs a series of results are derived which relate the information matrix, its inverse, the estimator of the treatment effects and the adjusted treatment sum of squares to those of its component designs. It is also shown that estimators of the stratum variances required for the recovery of information from between rows and between columns can be obtained by a relatively simple method.

SUMMARY Existing changeover designs given in the literature are not necessarily suitable when the treatments come from a factorial experiment. The concept of factorial structure in changeover designs is defined and shown to be a desirable requirement for these types of designs. Different classes of designs are then examined in the light of this concept. In particular, it is shown that all generalized cyclic (GC/n) changeover designs have factorial structure, thereby providing a flexible class of useful designs.

The Q"K statistic is employed to detect spurious observations in two-way tables, and the protection afforded by an estimation rule that omits response values detected as outliers is then examined. The main conclusions are that small and moderate size discrepancies are difficult to detect and that the protection afforded is surprisingly insensitive to the test level used for the Q"K statistic.

A combined dominant lethal-fertility study was conducted in which male and female Sprague-Dawley (CD) rats were exposed to 0, 30, 100 or 300 ppm of ethylene glycol monomethyl ether (EGME) vapor for 6 hr/day, 5 days/week for 13 weeks and then mated to untreated counterparts. Among males, fertility was completely suppressed after exposure to 300 ppm. A partial restoration of reproductive function was evident following 13 weeks of recovery. No treatment-related reproductive effects were observed among males exposed subchronically to 100 ppm, or among females exposed to 300 ppm or below of EGME. Studies to assess the effects of inhaled EGME on embryonal and fetal development were also conducted in Fischer 344 rats, CF-1 mice, and New Zealand White rabbits. Rats and rabbits were exposed to concentrations of 0, 3, 10 or 50 ppm for 6 hr/day on days 6-15 or 6-18 of gestation, respectively. Exposure of rabbits to 50 ppm resulted in significant teratologic effects, an increased resorption rate, and decreased fetal body weight. Slight fetotoxicity in the form of skeletal variations were observed among rats exposed to 50 ppm. Exposure of pregnant mice to 0, 10, or 50 ppm for 6 hr/day on days 6-15 of gestation resulted in slight fetotoxicity at 50 ppm. No significant treatment-related effects were observed at 10 ppm of EGME or below in any of the species tested. Separate groups of pregnant rats and rabbits were exposed to 0, 500, 1500 or 3000 ppm of propylene glycol monomethyl ether (PGME) during organogenesis.(ABSTRACT TRUNCATED AT 250 WORDS)

SUMMARY Factorial experiments can be set out in row-column designs using the generalized cyclic method of construction. From parallel results on block designs, it is shown how the confounding schemes and efficiency factors of such designs are obtained. Simple rules for constructing useful designs are given.

Summary In the study and construction of optimal block designs over the past 20 years a number of conjectures have been repeatedly stated and used. The purpose of this note is to bring together some of these conjectures. Although known to those actively engaged in research in design, it is hoped that this note will stimulate other statisticians and mathematicians to give their attention to these unsolved problems.

Pregnant Sprague-Dawley rats inhaled 0, 400, 1000, or 3000 ppm methyl ethyl ketone (MEK) for 7 hr/day on Days 6 through 15 of gestation. Maternal toxicity, as evidenced by decreased weight gain and increased water consumption, was observed among rats exposed to 3000 ppm MEK. Slight fetotoxicity was observed among litters of rats exposed to 3000 ppm MEK as evidenced by an increased incidence of two minor skeletal variants. The results of this study duplicate the increased incidence of skeletal variants observed in an earlier study by B. A. Schwetz, B. K. J. Leong, and P. J. Gehring (1974, Toxicol. Appl. Pharmacol. 28, 452–464), and do not indicate that inhaled MEK causes either an embryotoxic or teratogenic response in rats at exposure levels up to 3000 ppm.

Statistics offered by Cook (1977) and Andrews and Pregibon (1978) purport to reveal influential observations in a regression analysis. Detailed examination of these statistics shows that two different types of influence are being measured and this is illustrated with examples derived from a set of data given by Mickey, Dunn, and Clark (1967). Recommendations are given for obtaining the best use of the statistics available. KEY WORDS: Influential observationsOuthersRegressionResiduals

Summary The paper lists efficient and robust cyclic designs for 6 ≤ v ≤ 30, r ≤ 10 and r = ik (i ≥ 1).