Examination representation using adaptive testing: application in interview process
View/ Open
Date
2010Author
Gathitu, Leah Nyambura
Type
ThesisLanguage
enMetadata
Show full item recordAbstract
This research focused on the applicability of computer adaptive testing in the
selection of candidates from an interview process. A computer adaptive test adapts to
the ability of an individual student and presents questions that are suited to the
candidate's ability. It does this by revising the ability estimate of the individual as the
test progresses. With the revised ability estimate, the question that presents the most
~
information about the student is selected for presentation. The test progresses until the
change in ability estimation becomes negligible, meaning that the estimated ability is
very near the true ability of the student. After the stopping criterion is met and the test
completes, a report is immediately presented to the student indicating his performance
as a percentage score.
The research also looked at previous studies conducted on the subject and also
how interviews are conducted. The researcher identified that there is a gap and a need
to improve the interview process. The gap is that written interviews do not accurately
capture the ability of a student and therefore may result to good candidates being
eliminated from an interview. It is important that a test be able to capture the ability of
a student accurately so that the best candidates are selected. To demonstrate how such
a system works, a design, implementation and evaluation of a model of an adaptive
test was done, and then findings from the research were highlighted.
The research identifies the benefits and drawbacks of using the computer
adaptive test approach and also the areas that it is best applied and used.
Citation
Master of Science in Information SystemsSponsorhip
University of NairobiPublisher
University of Nairobi School of Computing and Informatics