Pregled bibliografske jedinice broj: 1162070
A Psychometric Analysis of the Emotional Skills and Competence Questionnaire (ESCQ-45) Using Item Response Theory
A Psychometric Analysis of the Emotional Skills and Competence Questionnaire (ESCQ-45) Using Item Response Theory // 25. Dani Ramira i Zorana Bujasa: međunarodni psihologijski znanstveni skup: knjiga sažetaka / Mikac, Una ; Mehulić, Jasmina (ur.).
Zagreb: Hrvatsko psihološko društvo (HPD), 2021. str. 16-16 (predavanje, domaća recenzija, sažetak, znanstveni)
CROSBI ID: 1162070 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
A Psychometric Analysis of the Emotional Skills
and
Competence Questionnaire (ESCQ-45) Using Item
Response Theory
Autori
Ćosić Pilepić, Ana ; Mohorić, Tamara ; Takšić, Vladimir
Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni
Izvornik
25. Dani Ramira i Zorana Bujasa: međunarodni psihologijski znanstveni skup: knjiga sažetaka
/ Mikac, Una ; Mehulić, Jasmina - Zagreb : Hrvatsko psihološko društvo (HPD), 2021, 16-16
Skup
25. Dani Ramira i Zorana Bujasa (DRZB)
Mjesto i datum
Zagreb, Hrvatska, 30.09.2021. - 02.10.2021
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Domaća recenzija
Ključne riječi
item response theory, multidimensional, graded response model, R, emotional competence, ESCQ-45
Sažetak
The Emotional Skills and Competence Questionnaire (ESCQ-45) was investigated by means of item response theory (IRT) modeling in a large cross- cultural sample (N = 5081 students from 13 countries). Different unidimensional polytomous IRT models (partial credit model, PCM ; generalized partial credit model, GPCM ; rating score model, RSM and graded response model, GRM) were compared with a multidimensional GRM model. We assessed model fit using an index, M2, which is specifically designed to assess the fit of item response models for ordinal data. We used the M2- based root mean square error of approximation as the primary fit index. We also used the standardized root mean square residual (SRMSR) and comparative fit index (CFI) to assess adequacy of model fit. After a series of comparisons, the findings indicated that the multidimensional GRM model was superior to all of the unidimensional models. In addition to global model-data fit and comparison, we assessed the item- level model data fit. For this assessment, we used a recommended index S-X2 and its RMSEA value, which was under the cut-off value of .06 for all items, indicating an adequate fit and substantive link of items to the latent trait. Once we established the adequacy of model and item fit, we computed both unidimensional and multidimensional item parameters. Slope (a) parameters ranged from 0.24 to 2.24, with Item 23 being most discriminating and Item 1 the least discriminating item of the scale. The location (b) parameters indicated that responses cover a wide range of the latent traits. The correlations between the latent traits were between .56 and .63. In addition, we analyzed all of the items individually using their category characteristic and item information curves, and the scale as a whole using scale information and scale characteristic curve. At the global level, the ESCQ-45 showed very good precision across most of the latent trait range.
Izvorni jezik
Engleski
Znanstvena područja
Psihologija
POVEZANOST RADA
Projekti:
NadSve-Sveučilište u Rijeci-uniri-drustv-18-28 - Konstrukcija upitnika za procjenu emocionalne kompetencije djece (Mohorić, Tamara, NadSve - UNIRI Sredstva potpore znanstvenim istraživanjima) ( CroRIS)
Ustanove:
Filozofski fakultet, Rijeka