DESIGN CONSIDERATIONS IN THE ESTIMATION OF INTRA-CLASS CORRELATION
DESIGN CONSIDERATIONS IN THE ESTIMATION OF INTRA-CLASS CORRELATION
复制标题
DOI：
10.1111/j.1469-1809.1982.tb00718.x
复制
发表时间：
1982-01-01
影响因子：
1.9
通讯作者：
KOVAL, JJ
中科院分区：
文献类型：
--
作者：
DONNER, A;KOVAL, JJ
当从k个家系中选出个个体时，考虑家系研究设计以估计组内相关系数p的值，i = 1，2，...，k。特别是，平衡设计的准确性（ni=n，i = 1，2，...，k）与非平衡“自然”设计的精度相比，其中，他们是从实际中往往出现的家庭规模分布中随机抽样的。发现对于p的两种不同的估计量，平衡设计通常是可取的，但只有在很小的程度上，如果抽样的家庭数大于50。
The design of family studies to estimate the value of an intraclass correlation coefficientpis considered whenniindividuals are to be selected from each ofkfamilies, i = 1, 2, …,k.In particular, the accuracy of a balanced design (ni=n, i = 1,2,…,k) for estimatingpis compared with the accuracy of an unbalanced ‘natural’ design, in which theniare sampled at random from family size distributions that tend to occur in practice. It is found for two different estimators ofpthat the balanced design is usually preferable, but only to a small degree if the number of families sampled is greater than 50.