Gruber Nicole, Kreuzpointner Ludwig
Department of Psychology, Universität Regensburg, Regensburg, Germany.
PLoS One. 2013 Nov 5;8(11):e79450. doi: 10.1371/journal.pone.0079450. eCollection 2013.
As frequently reported, psychometric assessments on Picture Story Exercises, especially variations of the Thematic Apperception Test, mostly reveal inadequate scores for internal consistency. We demonstrate that the reason for this apparent shortcoming is not caused by the coding system itself but from the incorrect use of internal consistency coefficients, especially Cronbach's α. This problem could be eliminated by using the category-scores as items instead of the picture-scores. In addition to a theoretical explanation we prove mathematically why the use of category-scores produces an adequate internal consistency estimation and examine our idea empirically with the origin data set of the Thematic Apperception Test by Heckhausen and two additional data sets. We found generally higher values when using the category-scores as items instead of picture-scores. From an empirical and theoretical point of view, the estimated reliability is also superior to each category within a picture as item measuring. When comparing our suggestion with a multifaceted Rasch-model we provide evidence that our procedure better fits the underlying principles of PSE.
正如经常报道的那样，对图片故事练习进行的心理测量评估，尤其是主题统觉测验的各种变体，大多显示出内部一致性得分不足。我们证明，这一明显缺陷的原因不是编码系统本身造成的，而是内部一致性系数，尤其是克朗巴哈α系数使用不当所致。通过将类别分数用作项目而非图片分数，可以消除这个问题。除了理论解释外，我们还从数学上证明了为何使用类别分数能产生充分的内部一致性估计，并使用海克豪森的主题统觉测验原始数据集以及另外两个数据集对我们的想法进行了实证检验。我们发现，将类别分数用作项目而非图片分数时，通常会得到更高的值。从实证和理论角度来看，估计的信度也优于将图片中的每个类别用作项目测量时的情况。在将我们的建议与多面Rasch模型进行比较时，我们提供了证据表明我们的方法更符合图片故事练习的潜在原则。
