Effect of Item Order on the Reliability of Mathematics Test among Secondary School Students in Rivers State

Abstract

The study investigated the effect of item order on the reliability of mathematics test among secondary school students in Rivers State. One research question and one null hypothesis guided the study. Quasi – experimental research design was used and the study was carried out in nine public senior secondary schools in three local government areas in River State which was drawn using Simple Random Sampling Technique. A sample size of 507 students were drawn from the population of 904 through Stratified Random Sampling Technique and the application of Taro Yemen formula to determine the minimum sample size. The instrument used was Multiple Choice Format Mathematics Performance Test (MCFMPT) arranged in ascending, descending and inconsistent order of difficulty and students’ scores were used for data collection. The reliability of the instrument was 0.75 using split-half method of establishing reliability and Spearman Brown prophecy formula for internal consistency of the instrument. Mean and Standard deviation were used to answer research question while t-test and Analysis of variance (ANOVA) were used to test the null hypotheses at 0.05 alpha level. The results revealed that item order based of ascending, descending and inconsistent order do not have significant effect on the reliability of mathematics test among secondary school students. Based on the findings, it was recommended that all pattern of item order (ascending, descending and inconsistent order of difficulty) should be encouraged among secondary school students as it has no significant effect on reliability coefficient. Students should be motivated to improve their real abilities in mathematics related courses and not judging their underperformance in mathematics based on the arrangement of items.