Predictive and postdictive success of statistical analyses of yield trials

Abstract

The accuracy of a yield trial can be increased by improved experimental techniques, more replicates, or more efficient statistical analyses. The third option involves nominal fixed costs, and is therefore very attractive. The statistical analysis recommended here combines the Additive main effects and multiplicative interaction (AMMI) model with a predictive assessment of accuracy. AMMI begins with the usual analysis of variance (ANOVA) to compute genotype and environment additive effects. It then applies principal components analysis (PCA) to analyze non-additive interaction effects. Tests with a New York soybean yield trial show that the predictive accuracy of AMMI with only two replicates is equal to the predictive accuracy of means based on five replicates. The effectiveness of AMMI increases with the size of the yield trial and with the noisiness of the data. Statistical analysis of yield trials with the AMMI model has a number of promising implications for agronomy and plant breeding research programs.

Genotype by Environment Interaction for Protein Content of Malt Barley Genotypes Using the Additive Main Effect and Multiplicative Interaction Effect Model (AMMI) and Genotype Plus Genotype by Environment Interaction (GGE) Biplot

“…The postdictive evaluation using the (Gollob, 1968) F-test the four interaction principal components were significant (p#0.01). The result was in agreement with Sivapalan et al (2000) recommended an AMMI model with the first four IPCAs predicates well the genotype by location interaction and the result was not consistent with Gauch and Zobel (1988) the two interaction principal component predictive while the reaming contributed to noise and Yan and Kang (2002) stated that most of the interaction occurs in the first few axes. The malt barley genotypes were predicted by the four interaction principal components while the rest of the interaction principal component might be attributed to the noise.…”

Análise AMMI da produtividade de grãos em linhagens de soja selecionadas para resistência à ferrugem asiática

“…Na definição do número de eixos principais a serem retidos para explicar e representar graficamente o padrão relacionado à interação GxE, adotaram-se critérios utilizados por Gauch & Zobel (1988), tendose levado em consideração a proporção da soma de Tabela 1. Identificação das linhagens de soja avaliadas (F 6 e F 7 ), com as respectivas genealogias.…”

Adaptabilidade e estabilidade de linhagens experimentais de soja selecionadas para caracteres agronômicos através de método uni-multivariado

“…Compreendeu três tipos de populações, obtidas de um dialelo parcial 4 x 4 envolvendo quatro genitores (IAC-100, Crockett, Lamar e D72-9601-1) resistentes a insetos e quatro cultivares adaptadas (BR-6, IAS-5, Davis, OCEPAR-4) com alta produtividade de grãos e precocidade (PINHEIRO, 1998 As análises de estabilidade e adaptabilidade fenotípica foram realizadas pelo método AMMI (ZOBEL et al 1988) por meio dos procedimentos GLM e IML do SAS e programa descrito por DUARTE e VENCOVSKY (1999). A técnica combinou método univariado (análise de variância) para componentes principais e trata a interação multiplicativa desses fatores com base na análise multivariada por componentes principais e decomposição por valores singulares.…”