Diseños Experimentales Con Testigos Repetidos Experimental Designs with Repeated Controls (original) (raw)
Related papers
Frontiers in Plant Science, 2021
Plant breeding programs use multi-environment trial (MET) data to select superior lines, with the ultimate aim of increasing genetic gain. Selection accuracy can be improved with the use of advanced statistical analysis methods that employ informative models for genotype by environment interaction, include information on genetic relatedness and appropriately accommodate within-trial error variation. The gains will only be achieved, however, if the methods are applied to suitable MET datasets. In this paper we present an approach for constructing MET datasets that optimizes the information available for selection decisions. This is based on two new concepts that characterize the structure of a breeding program. The first is that of "contemporary groups," which are defined to be groups of lines that enter the initial testing stage of the breeding program in the same year. The second is that of "data bands," which are sequences of trials that correspond to the progression through stages of testing from year to year. MET datasets are then formed by combining bands of data in such a way as to trace the selection histories of lines within contemporary groups. Given a specified dataset, we use the A-optimality criterion from the model-based design literature to quantify the information for any given selection decision. We demonstrate the methods using two motivating examples from a durum and chickpea breeding program. Datasets constructed using contemporary groups and data bands are shown to be superior to other forms, in particular those that relate to a single year alone.
Check plots in field breeding experiments
Biometrical Letters, 2013
Summary This paper deals with the problems of selection in the early stages of a breeding program. During the improvement process, it is not possible to use an experimental design that satisfies the requirement of replicating all the treatments, because of the large number of genotypes involved, the small amount of seed and the low availability of resources. Hence unreplicated designs are used. To control the real or potential heterogeneity of experimental units, control (check) plots are arranged in the trial. There are many methods of using the information resulting from check plots. All of the usually applied adjusting methods for unreplicated experiments are appropriate for some specific structure of soil fertility. Their disadvantage is the fact that, before and also after the experiment, we usually do not know what a kind of soil structure is present in the experiment. Hence we cannot say which of the existing methods is appropriate for a given experimental situation. The meth...
Designs for Test Treatments - Control(S) Comparisons
2000
In practice there may arise experimental situations where it is desired to compare several treatments called the test treatments to a standard treatment called control. The main interest here lies in making test treatment-control comparison with as much precision as possible and comparison within the test treatments are of less importance. For example in agricultural experiments, the aim of the
On-Farm Strip Trials vs. Replicated Performance Trials for Cultivar Evaluation
Crop Science, 2002
than performance trial plots. Each year, several hundred on-farm trials for winter wheat and over a thousand for A systematic comparison between two cultivar evaluation and recmaize (Zea mays L.) are conducted in Ontario. Only a ommendation systems, i.e., the balanced and replicated performance trials conducted in small plots at a small number of locations, and few cultivars (generally two, often Ͻ5) are evaluated in the unbalanced and non-replicated on-farm trials conducted in large a trial, however, and very often, different cultivars are strips on many farms, is lacking. This study was initiated to investigate tested in different trials, resulting in highly unbalanced the usefulness of the two contrasting systems in cultivar evaluation data. Consequently, utilization of strip-trial data has and the relationships between them. Yield data from Ontario winter been limited to paired comparisons, such as comparison wheat (Triticum aestivum L.) strip trials and performance trials for between a new cultivar and a standard check (Eskridge, 1998 to 2000 were analyzed by mixed models. For all 3 yr, results 1996), and only data from trials that included common from the two systems were highly correlated, both in terms of the cultivars can be used in such comparisons. Strip trials best linear unbiased predictors (BLUP) and for the t-values of BLUP. have not been used to make comparisons among all cul-Cultivars judged to be superior (or inferior) by one system were never judged to be inferior (or superior) by the other. Thus, both on-farm tivars. strip trials and replicated small-plot trials provide valid data for effec-Thus, each of the two test systems, the performance tive cultivar evaluation. On the basis of t-statistics, which measure trials and the strip trials, has pros and cons. The former cultivar reliability, cultivars can be classified into superior (t Ն 2), ingenerates balanced and replicated data from small-plots ferior (t Յ Ϫ2), and intermediate or inadequately tested (Ϫ2 Ͻ t Ͻ 2). in a limited number of locations (Ͻ10 for winter wheat Two cultivars can be regarded as different in reliability if their t-values in Ontario), whereas the latter generates highly unbaldiffer by Ն3. The evaluation power of strip trials for a cultivar depends anced and non-replicated data from large strips on nuon the number of trials in which the cultivar is tested; a cultivar may merous farms. Understanding the relationship between not be adequately evaluated if it is tested in fewer than 20 trials.
Simultaneous Selection for Yield and Stability in Crop Performance Trials: Consequences for Growers
Agronomy Journal, 1993
Utilization of genotype × environment (GE) interaction encountered in crop performance trials is an important issue among plant breeders and agronomists. Practical integration of yield and stability of performance has not been achieved. The purposes of this paper are (i) to examine consequences to growers when researchers commit Type I (rejecting the null hypothesis or Ho when it is true) and Type (accepting the Ho when it is false) errors under a yield-based, conventional selection method (CM) and a proposed method (yield-stability statistic or YSi) that uses GE interaction, and (ii) to show why a greater emphasis on the stability component would be advantageous to growers. A corn (Zea mays L.) dataset was used to compute the YSi and to estimate Type II error rates for overall mean yield comparisons and for the stability-variance statistic, σ2i(σ2i measures contribution of ith genotype to the total GE interaction) at different (Type I error rate) and δ (minimal detectable difference) levels. When pairwise yield comparisons are made, a higher level of a will not be as harmful to growers as a higher level of β (Type II) error rate). Since researchers would prefer to have power (1 - β) of a test between 0.70 and 0.80, choosing an α(1) level (one-tailed) between and 0.20 should be appropriate. If an α(1) value of 0.225 is selected δ between 1.0 and 1.4, the Type II error rate would be almost zero. For stability, the Ho tested was that yield means of a genotype in different environments were equal, i.e., σ2i = 0. A consequence of committing a Type I error would be that growers could miss using a stable cultivar, but a consequence of committing a Type II error can be disastrous for growers, as they could choose an unstable genotype and suffer economically. A greater emphasis on performance stability during selection would benefit growers. doi:10.2134/agronj1993.00021962008500030042x
Comparing the relative efficiency of two experimental designs in wheat field trials
This investigation was conducted in 2010/11 and 2011/12 growing seasons at the experimental farm of the Faculty of Agriculture, Cairo University, Giza, Egypt. Twenty Egyptian bread wheat cultivars were evaluated in an alpha lattice design with three replications for nine characters. The aim was to compare the relative efficiency of two experimental designs based on error mean squares. In field trials, variation in soil fertility can result in substantial heterogeneity within blocks and thus, poor precision in treatment estimates resulted. For this purpose, two datasets were analyzed according to alpha lattice design and randomized complete blocks design (RCBD). For the two trials, alpha lattice design exhibited more efficient than randomized complete blocks design in reducing both the error mean squares and the coefficient of variation consequently, an efficient estimation of treatment differences, than RCBD. Average estimated relative efficiency (RE) was 9.5, 28.5, 30.0, 22.5, 40.0, 30.5, 35.0 and 28.5% for plant height, number of tillers plant-1 , spike length, number of spikelets spike-1 , number of grains spike-1 , 1000-grain weight, grain yield plant-1 and grain yield feddan-1 , respectively, indicating that the high precision to estimate treatment effects is gained significantly from using an alpha lattice design instead of RCBD. Whereas RE value of 0.98 for days to 50% heading indicated that the precision of both alpha lattice design and RCBD was similar. Mean rank comparisons for both RCBD and alpha lattice design were performed. The ranks were not constant across the experiments. The results showed that the traditional RCBD should be replaced by alpha lattice in the agricultural field trials when the number of treatments to be tested in an experiment increases to more than ten, where a homogeneous block is quite difficult to find in field experiments. INTRODUCTION A correct experimental design is as important as a correct statistical analysis in order to obtain valid and reliable conclusion from field experiments. Certain restrictions must be imposed when the plots are arranged in order to be able to accurately estimate the errors. The choices of experimental design as well as of statistical analysis are of huge importance in field experiments. These are necessary to be correctly in order to obtain the best possible precision of the results. Wheat breeders and agronomists are faced a problem, how to select and evaluate the available experimental designs. The available literature of the efficiency of lattice designs relative to the randomized complete blocks design in wheat variety trials was very rare. The efficiency of one analysis over another is usually measured in terms of reduced error variance, expected error mean squares, or standard error of the difference between genotype means (Cochran and Cox, 1957, Binns 1987 and Magnussen 1990). The randomized block, latin square, and other complete block types of experiments are inefficient for comparing large number of treatments, because of their failure to adequately minimize the effect of soil heterogeneity (Lentner and Bishop 1993). Also, when the number of factors and/or levels of the factors increase, the number of treatment combinations increase very rapidly and it is not possible to accommodate all these treatment combinations in a single homogeneous block. Incomplete block designs arrange the total number of varieties in relatively small blocks that contain fewer varieties. Consequently, there is a gain in precision due to use of small blocks. As far as the layout of the incomplete block designs are no more difficult than randomized blocks. Some extra planning is involved in drawing up and randomizing the experimental plan. Randomized complete block design (RCBD) is affordable when the block size is less than eight varieties/treatments. It is always useful to use alpha lattice when the number of varieties/treatments increases. As a result of use a large number of treatments, estimate of experimental error is inflated and results are low in precision, so the use of RCBD is unsuitable when the
Federer and Crossa Screening Experimental Designs 2012.pdf
Crop breeding programs using conventional approaches, as well as new biotechnological tools, rely heavily on data resulting from the evaluation of genotypes in different environmental conditions (agronomic practices, locations, and years). Statistical methods used for designing field and laboratory trials and for analyzing the data originating from those trials need to be accurate and efficient. The statistical analysis of multi-environment trails (MET) is useful for assessing genotype × environment interaction (GEI), mapping quantitative trait loci (QTLs), and studying QTL × environment interaction (QEI). Large populations are required for scientific study of QEI, and for determining the association between molecular markers and quantitative trait variability. Therefore, appropriate control of local variability through efficient experimental design is of key importance. In this chapter we present and explain several classes of augmented designs useful for achieving control of variability and assessing genotype effects in a practical and efficient manner. A popular procedure for unreplicated designs is the one known as "systematically spaced checks." Augmented designs contain "c" check or standard treatments replicated "r " times, and "n" new treatments or genotypes included once (usually) in the experiment.
The analysis of variance of a data set made up of 30 sweet corn (Zea mays L.) hybrids evaluated over 5 years for marketable ears (dozens per hectare) indicated a significant genotype (hybrid) × year (GY) interaction. Three selection methods were compared: 1) a conventional method based on mean yield alone (YA), 2) Kang’s ranksum (KRS) method, and 3) Kang’s modified rank-sum (KMR) method. The number of hybrids selected on the basis of YA, KRS, and KMR was 13. The KRS selected the lowest number of unstable hybrids (three) compared with the YA and KMR, which selected eight and six unstable hybrids, respectively. The mean yields of the selected hybrids were 3034 dozen/ha for YA, 2945 dozen/ha for KRS, and 3019 dozen/ha for KMR. The mean yield of KRS-selected hybrids and KMR-selected hybrids was <2.9% and 0.5%, respectively, than that of YA-based selections. This yield reduction was regarded as insignificant considering the farmer would be able to choose more consistently performing hybrids on the basis of KRS than on the basis of KMR or YA. Heterogeneity due to environmental index is the mean of all genotypes in the jth year and X.. is the overall mean) was significant and was removed from the GY interaction. The removal of heterogeneity revealed that hybrids 77-2269, 116-Kandy Korn-EH, Golden Queen, 141-Sundance, Merit, and Stowell Evergreen were unstable because of a linear effect of the environmental index, and that hybrids 76-2681 and 806F-Truckers showed stable performance due to a linear effect of the environmental index.