Sammenlign metoder
Gjennomgå de valgte metodene side om side; rader som avviker, er uthevet.
| Innholdvaliditet i datamatisert adaptiv testing (CAT)× | Innholdsvaliditet× | |
|---|---|---|
| Fagfelt | Psykometri | Psykometri |
| Familie | Latent structure | Latent structure |
| Opprinnelsesår≠ | 1975 / 1980 | 1975 |
| Opphavsperson≠ | Lawshe (content validity); Lord & Weiss (CAT framework) | C. H. Lawshe (quantitative framework); earlier qualitative traditions in educational measurement |
| Type≠ | Validity evaluation / test design | Validity evidence / expert judgement procedure |
| Opprinnelig kilde | Lawshe, C. H. (1975). A quantitative approach to content validity. Personnel Psychology, 28(4), 563–575. link ↗ | Lawshe, C. H. (1975). A quantitative approach to content validity. Personnel Psychology, 28(4), 563–575. link ↗ |
| Alias | CAT content validity, adaptive item bank content coverage, content balancing in CAT, CAT blueprint validity | content-related validity, logical validity, face validity, content validation |
| Relaterte | 6 | 6 |
| Sammendrag≠ | Content validity in computerized adaptive testing (CAT) ensures that an adaptively administered assessment adequately samples the intended content domain despite delivering only a subset of items to each examinee. It integrates classical content validity methods with CAT-specific item bank design and content balancing algorithms to guarantee representative domain coverage at both the item bank and the individual test level. | Content validity is evidence that a measurement instrument adequately samples the full domain of the construct it is intended to measure. It is established through systematic expert review and quantified with indices such as Lawshe's Content Validity Ratio (CVR) and Lynn's Content Validity Index (CVI), making it the foundational validity step in scale development. |
| ScholarGateDatasett ↗ |
|
|