2012 Fiscal Year Final Research Report
Application of hierarchical linear modeling to test data
| Project/Area Number |
22730506
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Educational psychology
|
|---|
| Research Institution | Niigata University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2010 – 2012
|
| Keywords | テストデータ / 階層線形モデル / 信頼性 / 検定力 |
|---|
| Research Abstract |
Methodologies for analyzing hierarchically structured test datawere investigated. Two simulation studies showed that either log or cubic roottransformation performs better than other transformations in reliability generalizationstudies which adopt hierarchical linear modeling, and that hierarchical linear modeling isas powerful as latent growth modeling in the case of comparison between growth rates oftwo groups.
|
