方法对比
并排查看您选择的方法；存在差异的行会高亮显示。
| 计算机化自适应测试（CAT）中的构念效度× | 差异项目功能 (DIF)× | |
|---|---|---|
| 领域 | 心理测量学 | 心理测量学 |
| 方法族 | Latent structure | Latent structure |
| 起源年份≠ | 1989–2000s | 1970s–1993 |
| 提出者≠ | Samuel Messick (unified validity framework); CAT application formalized by Wainer, van der Linden, and colleagues | William H. Angoff and colleagues (ETS); systematized by Holland & Wainer |
| 类型≠ | Validity evaluation / psychometric evidence gathering | Item-level bias detection |
| 开创性文献≠ | Messick, S. (1989). Validity. In R. L. Linn (Ed.), Educational Measurement (3rd ed., pp. 13–103). American Council on Education / Macmillan. link ↗ | Holland, P. W. & Wainer, H. (Eds.) (1993). Differential Item Functioning. Lawrence Erlbaum Associates. ISBN: 978-0805809589 |
| 别名 | CAT construct validity, adaptive test construct validation, CAT validity evidence, construct validity evidence in CAT | DIF, item bias analysis, measurement non-equivalence, item-level measurement bias |
| 相关≠ | 6 | 5 |
| 摘要≠ | Construct validity in computerized adaptive testing evaluates whether the latent trait estimates produced by a CAT instrument genuinely measure the intended psychological or educational construct. Because adaptive algorithms select items individually for each examinee, the validity evidence gathered must account for the variable item exposure and the IRT-based scoring that are unique to CAT administrations. | Differential item functioning identifies test or survey items that behave differently for examinees from different groups — such as gender, ethnicity, or language background — after controlling for the underlying ability or trait being measured. DIF analysis is essential for fairness evaluation in educational testing and psychological scale development. |
| ScholarGate数据集 ↗ |
|
|