广义岭回归在家禽育种值估计中的应用

讨论了岭回归方法应用于混合线性模型方程组中估计家禽育种值的方法,其实质是将传统的混合线性模型方程组理解为一种广义岭回归估计,为确定遗传参数的估计提供了一种途径;同时,以番鸭为例,考虑了一个性状和两个固定效应,采用广义岭回归法对公番鸭育种值进行了估计,并与最佳线性无偏预测法(BLUP 法)进行了比较,结果表明,广义岭回归方法和BLUP 法估计的育种值及其排序非常接近,其相关系数和秩相关系数分别达到了0.998~(**)和0.986~(**),且采用广义岭回归法预测的误差率低(在±10%以内);表明在混合线性模型方程组中使用广义岭回归估计动物育种值的方法具有可行性,并可省去估计遗传参数的过程,使BLUP 法在动物选育中的应用更具实用性.

Generalized Ridge Regression and Its Application in Estimation of Breeding Values of Poultry

In this paper,a method named ridge regression,which can determine the k value with applying mixed linear model equations put by Henderson,is proposed to estimate breeding value of poultry.The essence is that mixed linear model equations is comprehended as generalized ridge regression.Meanwhile,One trait(70-day body weight) and two fixed effects(duck-shed effect and strain effect) are considered,and based on the data of 12 drakes(their 227 progeny distributed in two duck-shed),and the authors apply generalized ridge regression and BLUP methods to evaluate breeding value of 70-day weight of 12 male Muscovy.The results indicate that the conclusion of breeding value and its rank order of two methods are almost the same in general, and the relationship coefficient and rank correlation are 0.998~(**) and 0.986~(**) respectively,and using generalized ridge regression the range of error ratio of prediction is from-10% to 10%.These show that this method has feasibility and practical significance,and can avoid the procedure to estimate the hereditary parameter.