بناء اختبار تحصيلي في مادة منهجية البحث العلمي وفق نظرية الاستجابة للمفردة : نموذج راش
This study aims to employ the Rasch model to build an achievement test in the subject of scientific research methodology for a sample of second-year students in educational sciences at the University of Algiers 2 according to the item response theory (Rasch model), which consists of (35) questions in its initial form divided into three types of alternatives: multiple choice, true/ false, and fill-in-the-blanks, all of which contain only one correct answer (1) and one incorrect answer (0). To achieve the objectives of the current study, we used the descriptive analytical method appropriate to the nature of the study variables and applied the test to a sample representing the research community (students) that was chosen intentionally, numbering (110) male and female students from the Department of Educational Sciences in the state of Algiers. University of Algiers. To answer the study questions, many statistical analyses were used, including: standard deviation, arithmetic mean, variance, factor analysis using the basic components method of the residuals. For the developed Rasch model, WINSTEPS Version 3.72.3 program. After conducting the statistical analysis of the data, the results of the study were as follows: The test achieved the assumption of one-dimensionality and the test achieved the assumption of positional independence of measurement. 4 statements out of 35 statements and 6 individuals out of (110) male and female students were deleted for not conforming to the Rush Master model. The test has high stability, as the stability coefficient for the paragraphs reached (0.92) and the separation index reached (4.80) while the stability coefficient for individuals (students) reached (0.91) and the separation index reached (3.33). The results reached can be considered a scientific addition that enhances what previous studies have reached. This agreement was not the result of chance, but rather the result of the test's specifications embodied in three important facts related to the test itself in terms of its reliance on a solid theoretical framework and its containing 35 statements, and this number in itself is considered acceptable by researchers. (Published abstract)