ABSTRACT

The study detected Differential Item Functioning (DIF) in Economics multiple choice standardized test in Nigeria. Ten (10) research questions were asked and ten (10) hypotheses were formulated to guide the study. Mixed-Multi-Design approach was used in this study. The design of this study incorporated inferential survey and correlation methods. The population of the study was 4,434,979 secondary school students in the 11,875 public secondary schools in the 36 states including Abuja the Federal Capital Territory (FCT) of Nigeria. The sample comprised of seven hundred and ninety eight (798) students. Stratified, purposive, multi stage, cluster and simple random sampling techniques were used. The instruments for data collection were Socio-Demographic Inventory (SDI) and a 50-item-WAEC General Economics Paper I Multiple Choice Test. The instruments were re-validated by five specialists: three in Educational Measurement and Evaluation and two from Economics Education from Michael Okpara University of Agriculture Umudike and Imo State University, Owerri. The reliability of the test was re-established using Kuder-Richardson formular 20 (KR-20) statistics with an index of 0.83. In answering the research questions, binary logistic regression statistics was used to identify DIF in research questions 1-6. Binary Logistic Regression and Mantel-Haenszel Chi-Square were used to answer research question 7 by comparing their detection strength. Research question 8 was answered using IRT-Binary Logistic Regression method, research question 9 was answered using Biserial Correlation and Contingency Correlation Statistics. Research question 10 was answered using Nagelkerke R-Square statistics. Hypotheses 1-6, 8 & 10 were tested using Wald test associated with binary logistic regression statistics while hypothesis 7 was tested using Wald test associated with binary logistic regression statistics and Chi-Square test of independence associated with Mantel-Haenszel Chi-Square statistics. Hypothesis 9 was tested with t-test of simple linear correlation and Chi-Square test of independence. All the hypotheses were tested at 0.05 level of significance. Result of the analysis revealed among others that; DIF exist among the items in 2015 WAEC Economics multiple choice test with respect to the students’ gender, location, school ownership, socio-economic status, ethnic group and school type. The study further revealed that Binary Logistic Regression Statistics and Mantel-Haenszel Chi-Square Statistics detected equal number of 13 items as having gender-based DIF. Based on the findings, the researcher recommended that; WAEC test developers, other examination bodies and evaluators should be mindful of the disparities that exist between students’ gender, location, school ownership, socio-economic status, ethnic group and school type when setting examination items.