DETECTION OF BIOLOGICAL SEX - AN EMPIRICAL-TEST OF CLUSTER-METHODS
DETECTION OF BIOLOGICAL SEX - AN EMPIRICAL-TEST OF CLUSTER-METHODS
复制标题
DOI：
10.1207/s15327906mbr1504_6
复制
发表时间：
1980-01-01
影响因子：
3.8
通讯作者：
MEEHL, PE
中科院分区：
文献类型：
--
作者：
GOLDEN, RR;MEEHL, PE
对聚类法[6]进行了实证试验，评估了它们解决虚拟问题的能力，即检测人类生物性别的潜在分类。每个聚类法用于4套性别甄别自报人格兴趣问卷条目。每个项目指标的有效性是以生物性别作为标准变量进行实证检验的。构建了4套生物性项目指标，使其平均项目指标效度有所不同。在聚类法中，3种方法在大多数试验中准确地检测了生物性别分类，其他3种方法很少准确。对于检测真实的经验类，聚类方法的价值是值得怀疑的，因为我们通常不能保证聚类可能是准确的并且不是虚假的。使用内部效度或一致性测试可以消除这一缺点。
Cluster methods [6] were subjected to empirical trials evaluating their ability to solve a dummy problem, that of detecting an underlying taxonomy of biological sex in humans. Each cluster method was applied to 4 sets of sex-discriminant self report personality-interest questionnaire items. The validity of each item-indicator was empirically determined using biological sex as a criterion variable. The 4 sets of item-indicators of biological sex were constructed so as to vary in their average item-indicator validity. Of the cluster methods, 3 accurately detected the biological sex taxonomy in most of the trials; the other 3 methods were seldom accurate. For detecting real empirical classes, the cluster methods are of questionable value since we typically lack assurance that the clusters are likely to be accurate and not spurious. The use of internal validity or consitency tests may eliminate this shortcoming.