Abstract
The study examined the differential item functioning (DIF) of 2018 Basic Education Certificate examination (BECE) in Mathematics tests of National Examination Council (NECO) and BECE of Akwa Ibom State government in Nigeria. The invariance in the tests with regards to sex was considered using Item Response Theory (IRT) approach. The study area was Akwa Ibom state of Nigeria having a student population of 58,281 for the examination. The sample was made of up 3810 students drawn through a multi-stage sampling approach. The multidimensional IRT (MIRT) package implemented in R-programming language software was applied in analyzing the data. The findings reveal that BECE of NECO displayed 23(38.3%) DIF items while BECE of Akwa Ibom State had 37 (61.7%) DIF items in terms of sex. The findings also revealed that, in the two examinations, more items favoured the male candidates more than the female candidates in terms of performance. It was recommended that IRT model should be adopted by test developers to determine item parameters for selection of good items to ensure quality of items before administration. Test equating of students who write equivalent form examinations conducted by different examining bodies was also recommended for admission and placement of candidates to determine actual group differences in performance. The study posits that research on Differential Item Functioning is inconclusive, so should be encouraged.
Keywords Differential item functioning  invariance  multidimensional  item response theory  R-programming
Categories (categorize this paper)
Options
Edit this record
Mark as duplicate
Export citation
Find it on Scholar
Request removal from index
Revision history

Download options

PhilArchive copy

 PhilArchive page | Other versions
External links

Setup an account with your affiliations in order to access resources via your University's proxy server
Configure custom proxy (use this if your affiliation does not provide a proxy)
Through your library

References found in this work BETA

No references found.

Add more references

Citations of this work BETA

No citations found.

Add more citations

Similar books and articles

Analytics

Added to PP index
2022-01-22

Total views
67 ( #174,699 of 2,533,585 )

Recent downloads (6 months)
37 ( #23,902 of 2,533,585 )

How can I increase my downloads?

Downloads

My notes