A method to examine the reliability and the validity of measurement using multirater data

2017 Fiscal Year Final Research Report

• Project/Area Number: 26780362
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Educational psychology
• Research Institution: Tokyo Women's Medical University (2017); Waseda University (2014-2016)
• Principal Investigator: KUBO Saori 東京女子医科大学, 医学部, 助教 (70631943)
• Project Period (FY): 2014-04-01 – 2018-03-31
• Keywords: multitrait-multiraterデータ / 360度評価 / 収束的妥当性 / 弁別的妥当性 / 信頼性 / 確認的因子分析モデル

Outline of Final Research Achievements

In this study, two methods of analysis in order to examine reliability, convergent validity and discriminant validity of measurement using multitrait-multirater data are proposed in the framework of confirmatory factor analysis model. The first method is to evaluate reliability and validity using weighted sum scores of ratings by multiple raters. The second method is to deal with the data including a number of raters within a same rating source. As a result of application example to actual data, the usefulness of these methods was suggested. In the future, practical use of these methods in various fields such as 360-degree feedback is expected.

Free Research Field

心理統計学，教育測定