论文部分内容阅读
本研究采用Rasch测量理论中的评分量表模型探析一项自我评估量表的效度。根据解释性效度论据理论,本研究提出量表效度的四个关键性理据,并采用Rasch分析检查这四个效度理据的准确性与合理性。本研究中,我们采用一系列Rasch分析方法,包括信度分析、描述语与模型的拟合度分析、因子分析与试题差异分析等。同时,我们还研究了Rasch模型下被试的自评能力测量值与他们的客观水平测试成绩之间的相关性。研究结果表明,量表的信度良好,基本为单一的能力维度结构,量表的类别设置也比较合理。被试的自评能力值与客观水平测试成绩之间显著相关。本研究的分析结果为四个效度理据提供了重要支撑,本研究所采用的效度研究方法也为量表的效度研究提供了重要参考。
In this study, the validity of a self-rating scale was explored using the scoring scale model in Rasch’s measurement theory. According to the theory of explanatory validity argument, this study proposed four key rationales of validity of the questionnaire, and used Rasch analysis to examine the accuracy and rationality of the four validity arguments. In this study, we use a series of Rasch analysis methods, including reliability analysis, description of fit and similarity of models, factor analysis and test item difference analysis. At the same time, we also study the correlation between subjects’ self-assessment ability test and their objective level test scores under the Rasch model. The results show that the reliability of the scale is good, the basic structure of a single capacity dimension, the scale of the class settings are more reasonable. There was a significant correlation between subjects’ self-assessment ability and objective level test scores. The results of this study provide important support for the four rationales of validity, and the validity research methods used in this study provide an important reference for the validity of the scale.