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

对应用几种统计模型评价甘蔗品种稳定性的比较(英文)

[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.

[目的]比较研究用以评价甘蔗品种稳定性的三种模型。[方法]以广东省2009年甘蔗品种区域试验产量数据为例,对线性回归模型、AMMI模型和LRPCA模型在评价甘蔗品种稳定性方面的应用进行了比较。[结果]回归法计算简便、直观,AMMI模型和LRPCA模型的分析结果则更全面、深入,而这两种模型之间仍存在着一定差异。[结论]实际操作中,在根据不同的数据资料选择相适宜的分析方法的同时,也可以采用不同的方法进行分析,通过比较选择较为合理的结果。