Project/Area Number |
08610130
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
教育・社会系心理学
|
Research Institution | Bunkyo University (1998) Okayama University (1996-1997) |
Principal Investigator |
FUJIMORI Susumu Bunkyo University, Faculty of Human Science, Associate Professor, 人間科学部, 助教授 (00173477)
|
Project Period (FY) |
1996 – 1998
|
Project Status |
Completed (Fiscal Year 1998)
|
Budget Amount *help |
¥1,100,000 (Direct Cost: ¥1,100,000)
Fiscal Year 1998: ¥200,000 (Direct Cost: ¥200,000)
Fiscal Year 1997: ¥300,000 (Direct Cost: ¥300,000)
Fiscal Year 1996: ¥600,000 (Direct Cost: ¥600,000)
|
Keywords | arithmetical / mathematical ability / achievement level / item response theory / equating / 同時尺度調整法 / テスト / EMアルゴリズム / 数学学力 / 誤りパターン / 無答 |
Research Abstract |
In the last fiscal year for investigation, the study on the formulation of scale for the case when multiple examinations are performed for multiple groups progressed. In order to determine the achievement level in arithmetic and mathematics, it is necessary to produce a scale common to all grades. Therefore, the conclusion that it is appropriate to perform formulation and estimation of model parameters sinaultaneously based on the data of achievement tests that show that there is a difference in academic achievement between grades, was formed in the item response theory. In the investigation, an evaluation was made by conducting a simulation. The evaluation proved that it is appropriate to estimate model parameters by estimating the average between the achievements of students in each grade, and that the results of formulation improve in proportion to the increase in common items. Hence, 4612 students from third to ninth grade underwent examinations. Based on the answers to their 697 questions and the data obtained in the evaluation above, a common scale was produced and each grade's achievement level was finally determined. Thday, it is necessary to change from relative evaluation to achievement evaluation. This common scale makes achievement evaluation possible.
|