Estimating parameters of the family-size distribution in ascertainment sampling schemes: numerical results.
Estimating parameters of the family-size distribution in ascertainment sampling schemes: numerical results.
复制标题
确定抽样方案中家庭规模分布参数的估计：数值结果。
作者：
W. Ewens;B. Asaba
有人认为，在使用来自不同规模家庭的数据的任何确定抽样方案中，从来没有必要为（未知的）家庭规模分布假设特定形式。存在一种简单的条件方法，不对家庭规模分布做出任何假设，这总是优于任何特定分布形式的假设。此外，条件方法的简单性使人们能够深入了解遗传和确定参数估计的属性，而当假设家庭规模分布的特定形式时，这些属性是不可用的。
It is argued that, in any ascertainment sampling scheme using data from families of various sizes, there is never any need to assume a particular form for the (unknown) family-size distribution. There exists a simple conditional method, making no assumptions about the family-size distribution, that is always preferable to the assumption of any particular distributional form. Furthermore, the simplicity of the conditional method gives insights into properties of estimates of genetic and ascertainment parameters, which are not available when a particular form for the family-size distribution is assumed.