Nalazite se na CroRIS probnoj okolini. Ovdje evidentirani podaci neće biti pohranjeni u Informacijskom sustavu znanosti RH. Ako je ovo greška, CroRIS produkcijskoj okolini moguće je pristupi putem poveznice www.croris.hr
izvor podataka: crosbi !

Using of Structural Equation Modeling Techniques in Cognitive Levels Validation (CROSBI ID 291885)

Prilog u časopisu | izvorni znanstveni rad | međunarodna recenzija

Ćurković, Natalija Using of Structural Equation Modeling Techniques in Cognitive Levels Validation // Interdisciplinary description of complex systems, 10 (2012), 3; 270-283. doi: 10.7906/indecs.10.3.5

Podaci o odgovornosti

Ćurković, Natalija

engleski

Using of Structural Equation Modeling Techniques in Cognitive Levels Validation

When constructing knowledge tests, cognitive level is usually one of the dimensions comprising the test specifications with each item assigned to measure a particular level. Recently used taxonomies of the cognitive levels most often represent some modification of the original Bloom’s taxonomy. There are many concerns in current literature about existence of predefined cognitive levels. The aim of this article is to investigate can structural equation modeling techniques confirm existence of different cognitive levels. For the purpose of the research, a Croatian final high-school Mathematics exam was used (N = 9626). Confirmatory factor analysis and structural regression modeling were used to test three different models. Structural equation modeling techniques did not support existence of different cognitive levels in this case. There is more than one possible explanation for that finding. Some other techniques that take into account nonlinear behaviour of the items as well as qualitative techniques might be more useful for the purpose of the cognitive levels validation. Furthermore, it seems that cognitive levels were not efficient descriptors of the items and so improvements are needed in describing the cognitive skills measured by items.

cognitive levels ; structural equation modeling ; validity

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

Podaci o izdanju

10 (3)

2012.

270-283

objavljeno

1334-4684

10.7906/indecs.10.3.5

Povezanost rada

Psihologija

Poveznice
Indeksiranost