TESTS FOR RANK CORRELATION COEFFICIENTS .1.
TESTS FOR RANK CORRELATION COEFFICIENTS .1.
复制标题
DOI：
10.1093/biomet/44.3-4.470
复制
发表时间：
1957-01-01
期刊：
影响因子：
2.7
通讯作者：
PEARSON, ES
中科院分区：
文献类型：
--
作者：
FIELLER, EC;HARTLEY, HO;PEARSON, ES
下面是对所有抽样数据计算的第三个系数，我们希望以后考虑：（c）费舍尔-耶茨系数。令6（i I n）是所谓的正态顺序统计量，即来自正态总体的n个观测样本中第i个最大标准化偏差的期望值。然后，我们可以将这些得分值附加到u排名和v排名。Fisher & Yates（1938，p.50）建议，等级相关的度量可以从这些分数的积矩相关系数中获得，即rFE 6（i In）6（vi In）/62（i In）。(4)i= 1/i
The followilng is a third coefficient which has been computed for all the sampling data and which we hope to consider later:(c) The Fisher-Yates coefficient. Let 6 (i I n) be a so-called normal order statistic, ie the expected value of the ith largest standardized deviate in a sample of n observations from a normal population. Then we may attach these score values to both the u rankings and the v rankings. Fisher & Yates (1938, p. 50) have suggested that a measure of rank correlation might be obtained from the product moment correlation coefficient of these scores, namely rF E 6 (i I n) 6 (vi I n)/62 (i 1 n).(4) i= 1/i