Arab Educational Information Network

The current study aimed at detecting the effects of changing the location of the correct alternative in a multiple choice test on the difficulty estimates of items and estimates of the ability of individuals using the Rush model. To achieve the aims of the study were built achievement test of multiple choice with four alternatives in educational measurement and evaluation scheduled for students of General Education Diploma consisting of (34) items in the final form of test. It contains three models that had the same content and the variable was the correct alternative site. The first model was the correct alternative site on alternatives A and B. The second model was the correct alternative position on alternatives C, D, and the third model randomly distributed the correct alternative on the four different alternatives. The three models were applied to a random sample of (1541) students from the University of Tabuk. The researcher used the SPSS15, Bilog-Mg3 software to analyze the data for each of the three test models according to Rush model. The results of the study showed that there were no statistically significant differences between the arithmetic means of items difficulty coefficients due to the location of the correct alternative, and no statistically significant differences between the arithmetic means of the individual's ability parameter estimates due to the location of the correct alternative. (Published Abstract)