作物区试中的品种合理评估问题

以江苏省小麦品种区试资料为例,探讨对品种的合理评估问题。(1)优度估计。对品种×环境资料算出的品种总优势度,定义为通过全部试点中平均的品种响应值与最大响应值间的距离均方。其中的对照仅视为一个在某一试点中有可能是最大响应值的一个品种,而不须作为对参试品种评价的标准。这可容许育种者选设地区适应的品种作为对照时以较大的灵活性。(2)参数分组佔计。试点按产量水平及其变异度分为几个组,分组评定各品种的稳定性。这样的分析,可以给予各参试品种以更合理的评价。

Comparison of Several Statistical Analysis Models for Genotypic Stability of Saccharum officinarum

[Objective] The study aimed to compare several statistical analysis models for estimating the sugarcane （Saccharum spp.） genotypic stability. [Method] The data of sugarcane regional trials in Guangdong, in 2009 was analyzed by three models respectively： Finlay and Wilkinson model： the additive main effects and multiplicative interaction （AMMI） model and linear regression-principal components analysis （LR- PCA） model, so as to compare the models. [Result] The Finlay and Wilkinson model was easier, but the analysis of the other two models was more comprehensive, and there was a bit difference between the additive main effects and multiplicative inter- action （AMMI） model and linear regression-principal components analysis （LR-PCA） model. [Conclusion] In practice, while the proper statistical method was usually con- sidered according to the different data, it should be also considered that the same data should be analyzed with different statistical methods in order to get a more reasonable result by comparison.

Cultivar Selection and Test Site Evaluation of Cotton Regional Trials in Jiangsu Province Based on GGE Biplot

This study was to evaluate the high yielding and stability of candidate cultivars, depict the adaptive planting region, analyze trial location discrim-ination ability and representativeness, as wel as identify the ideal cultivar and trial location, with the aim to provide theory background for cultivar selection and rea-sonable scheme of test location in Jiangsu Province. [Method] The GGE biplot method was used to analyze the lint cotton yield of 12 experimental genotypes in the 6 test locations （three replicates in each） of the cotton regional trial in Jiangsu Province in 2013. [Result] The effects of genotype （G）, environment （E）, and geno-type by environment interaction （G＆#215;E） on lint cotton yield were al highly significant （P〈0.01）, which made it necessary to further explore the specific pattern of geno-type by environment interaction. Jinmian118 （G4） and SF3303 （G5） were the best ideal genotypes screened by the ＂ideal cultivar＂ and ＂ideal location＂ view of GGE biplot, and the ordination of test sites based on the ideal index were in the order of Dafeng （DF）, Yanliang （YL）, Liuhe （LH）, Dongtai （DT）, Yancheng （YC）, and Nantong （NT）, among which NT was relatively weak in representing of the whole target cot-ton planting region in Jiangsu Province. The ＂similarity among locations＂ view of GGE biplot clustered al trial locations into one group, showing that the test sites in the cotton planting region in Jiangsu Province were in the same mega-environment. The ＂which-won-where＂ view of GGE biplot indicated that cotton cultivar Jinmian118 （G4） was the most appropriate cultivar in the homogeneous cotton planting region in Jiangsu Province. [Conclusion] Among the candidate cultivars, Jinmian118 and SF3303 were identified as the most ideal cultivars in this set of conventional cotton regional trial in Jiangsu Province; the test site of Dafeng ranked the first out of al locations in terms of discrimination and representativeness, and al test locations were clustered into the same mega-environmet, which indicated the high efficiency of cultivar selection in the cotton regional trial in Jiangsu Province.

Evaluation on the High Yielding, Stability and Comprehensive Performances of Check Cultivars in National Cotton Regional Trials in the Yangtze River Valley

[Objective] This study was to analyze the high yielding, stability, adaptabil-ity and main characteristics of check cultivars in national cotton regional trials in the Yangtze River Val ey in 2000-2013, with the aim to provide theoretical basis for the reasonable selection of check cultivars for cotton regional trials. [Method] GGE biplot analysis method was used to carry out the intensive analysis and comprehensive comparisons on the performances and differences of the 9 major characters of check cultivars, namely, lint cotton yield , stability, and other main traits including bol weight, bol number, lint percentage, fiber length, fiber strength, micronaire val-ue, plant height and seed index. [Result] Ezamian 10 was suitable in the majority of cotton planting regions in the Yangtze River Val ey, with the best high yielding abili-ty and perfect yield stability. The yielding ability of Xiangzamian 8 ranked the sec-ond, but its stability was the poorest. Xiangzamian 8 was of the specific adaptive cultivar with relatively good performance in high yielding but the poorest stability. The suitable planting areas of Xiangzamian 8 were limited to the cotton planting re-gion around Dongting Lake in Hunan province, Poyang Lake in Jiangxi Province, the Coastal region in Jiangsu Province and Wuhan district in Hubei Province. Xi-angzamian 2 performanced poorer in both yielding and stability, while Simian 3 ranked first in stability but the last in yielding ability. The dominant character of Xi-angzamian 8 and Xiangzamian 2 were high cotton plants and big bol s. Simian 3 performanced super in lint percentage and fiber length. Ezamian 10 was strong in cotton bol formation ability, lint cotton yielding, fiber strength and seed size, as wel as high micronaire value. [Conclusion] The outstanding performance of Ezamian 10 in high and stable yield in the Yangtze River Val ey in recent years has effectively promoted the high yielding ability of candidate varieties in cotton regional trials in the area.