Differential Item and Bundle Functioning in Educational Testing Contexts
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Chan Yin Wah Fiona.
To enhance the fairness of educational tests, it is important to identify the causes of item bias. However, little progress has been made in understanding why differential item functioning (DIF) in educational tests occurs. Shealy and Stout (1993) proposed a multidimensional model of DIF according to which DIF occurs when an item measures some other dimensions besides the one that the test was supposed to measure. Douglas et al. (1996) made an extension to this model in which item bundles are formed based on the item characteristics that could be the reason for DIF and analysed for differential bundle functioning (DBF). This strategy is appropriate for testing different hypotheses about the reasons for group differences in item performance. DBF analyses have higher statistical power than DIF analyses as a result of amplification of the differences that could be statistically undetected in the single item approach (Nandakumar, 1993). In this talk I will present how DIF and DBF analyses can be used in exploring gender differences in mathematics item performance.
This talk is part of the Cambridge Psychometrics Centre Seminars series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|