Estimating Trait, Method, and Error Variance: Generalizing across 70 Construct Validation Studies
分析了70个已发表数据集的构念效度结果，发现特质平均解释不到50%的方差，质疑了假设测量误差极小或未正确建模系统误差的统计方法。
The authors examine the construct validation results of 70 published data sets. The analysis shows that, on average, traits account for less than 50% of the variance in construct measures. These findings raise questions about the application of statistical techniques that assume minimal measurement error or do not properly model systematic measurement error.