Effect of Multidimensional Ability Differences Across Groups of Examinees on Unidimensional Ability Estimation
Khoju, Madhab Raj
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/79871
Description
Title
Effect of Multidimensional Ability Differences Across Groups of Examinees on Unidimensional Ability Estimation
Author(s)
Khoju, Madhab Raj
Issue Date
2005
Doctoral Committee Chair(s)
Louis A. Roussos
Department of Study
Education
Discipline
Education
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Education, Tests and Measurements
Language
eng
Abstract
Zhang and Stout (1999) have demonstrated that the unidimensional ability composite of a multidimensional test to be a standardized linear combination of multiple abilities. Both simulated test data and real ACT test data were used to investigate the effect on unidimensional ability estimates of a group of examinees that are dimensionally different from other groups of examinees. BILOG was used to estimate examinee abilities for each of the three group datasets separately, and also for the combined dataset. Estimated abilities of the same group of examinees based on separate model calibrations were equated and compared. These equated abilities were used to analyze their differences both at the group and individual level. The results based on simulated data indicate that examinee ability estimates for dimensionally different groups depended on the dataset used for estimation. Such a result may be attributed to the fact that the test dimensionality differed across simulated datasets. On the other hand, for real test data, in addition to examinee ability estimates, the ACT scale score differences were also investigated both at the group level and at the individual examinee level. The ACT scale scores of the examinees based on combined dataset were not much different from the ACT scale scores based on ethnic group specific datasets both at the group and individual level. Such a result may be attributed to the fact that the test dimensionalities did not differ that much across ethnic groups.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
