【摘 要】
：
Differential Item Functioning(DIF) occurs when individuals from different populations show different probabilities of correctly responding to an item with the same latent trait.If DIF items exist in t
【机 构】
：
Boston College,USA
论文部分内容阅读
Differential Item Functioning(DIF) occurs when individuals from different populations show different probabilities of correctly responding to an item with the same latent trait.If DIF items exist in the assessment,the analysis results of individuals responses will no longer reflect their true abilities alone.
其他文献
Growth curve models are often used to investigate growth and change phenomena in the social,behavioral,and educational sciences and are one of the fundamental tools for dealing with longitudinal data.
Item Response Theory(IRT) is considered as superior to Classical Test Theory(CTT) and its use has been advocated in change assessment and beyond.
Scores from test batteries are usually used for making high-stakes decisions for placement,admission,and certification.It is thus vital to develop appropriate composite score and make adequate classif
Because of relatively small effect and sample sizes,many psychological studies are underpowered.Even if researchers understand the importance of well-powered research designs,their intuitions about po
A Monte Carlo study was carried out to examine the performance of two-group multivariate means comparison under the conditions of homogeneous and heterogeneous variance-covariance matrices across two
This study develops an effect size(ES;AG ) that is robust to violations of data assumptions – multivariate normality and homogeneity of covariance matrices – in Multivariate Analysis Of VAriance(MANOV
LASSO penalization can be used for models with very high numbers of covariates.The regression parameters are penalized and more of them become zero as the penalty increases,thereby resulting in covari
As a commonly used tool for operationalizing measurement models,Confirmatory Factor Analysis(CFA) requires strong assumptions that may lead to poor fit of the model to real data.The post-hoc modificat
Identification of subgroups of patients for which treatment A is more effective than treatment B,and vice versa,is of key importance to the development of personalized psychological medicine.
Many procedures have been developed to investigate DIF in questionnaire response data,among others the wellknown Likelihood-Ratio test and the Mantel-Haenszel statistic(see Magis et al.(2010) for a co