Individual response spread in self-report scales: Personality correlations and consequences
Individual response spread in self-report scales: Personality correlations and consequences
复制标题
DOI：
10.1016/s0191-8869(97)00175-x
复制
发表时间：
1998-03-01
影响因子：
4.3
通讯作者：
Dent, JB
中科院分区：
文献类型：
--
作者：
Austin, EJ;Deary, IJ;Dent, JB
我们认为，在使用问卷量表的个体差异的现象，并检查其后果。结果从两个说明性的研究，农民和顾问医生被用来证明，个人的标准差的反应选项的使用是一个一致的特质，这是显着相关的个性维度的积极性。还设计了一个数学模型的个人响应传播，它表明，独立项目的响应之间的显着虚假的相关性可能会出现。该模型通过估计来自我们的两个说明性数据集的个体响应阈值来扩展;使用这些阈值的数值模拟证实了伪相关性的发生。相关系数r的分布也与用于估计显著性水平的标准形式非常不同。这些观察结果对于分析自我报告数据的标准多变量方法有广泛的影响。(C)1998爱思唯尔科技有限公司版权所有。
We consider the phenomenon of individual differences in the use of questionnaire scales and examine some of its consequences. Results from two illustrative studies on farmers and consultant doctors are used to demonstrate that individual standard deviation of response option usage is a consistent trait which is significantly correlated with the personality dimension of conscientiousness. A mathematical model of individual response spread is also devised and it is shown that significant spurious correlations between responses to independent items can arise. This model is extended by estimating individual response thresholds from our two illustrative data sets; numerical simulation using these thresholds confirms the occurrence of spurious correlations. The distribution of correlation coefficients r is also very different from the standard form used for estimating levels of significance. There are widespread consequences of these observations for standard multivariate methods of analysing self-report data. (C) 1998 Elsevier Science Ltd. All rights reserved.