Statistical comparison between a separate volume method and a brief version method

2015 Fiscal Year Final Research Report

• Project/Area Number: 25730024
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Statistical science
• Research Institution: University of Tsukuba
• Principal Investigator: OZAKI Koken 筑波大学, ビジネスサイエンス系, 准教授 (50574612)
• Project Period (FY): 2013-04-01 – 2016-03-31
• Keywords: 心理学調査 / 因子分析 / 構造方程式モデリング / 短縮版 / 信頼性 / 妥当性 / 欠測データ解析

Outline of Final Research Achievements

In psychological research, constructs such as extroversion or self-esteem are often used. To measure such constructs, questionnaires are usually used. However, we sometimes need many items to measure one construct. Therefore, in psychological research, a brief version of the original questionnaires is often used. However, because a brief version is not the original version, the brief version sometimes lacks reliability or validity. In this research, a separate volume method is developed, which reduces the number of response items such as the brief version method for each respondent, but can collect the data for all of the original version. Some statistical characteristics are examined and the results show that the developed method is superior to the brief version method in some respects.

Free Research Field

統計学