Mohammad Mehdi Dorri; Abolfazl Rafiepour
Abstract
A big source of Rational number misconception is the "natural number bias". This term refers to the Interference of natural number knowledge in rational numbers. The research literature points at three main aspects where natural number knowledge are inappropriately Interfered in rational numbers tasks: ...
Read More
A big source of Rational number misconception is the "natural number bias". This term refers to the Interference of natural number knowledge in rational numbers. The research literature points at three main aspects where natural number knowledge are inappropriately Interfered in rational numbers tasks: "density", "operations", and "size". The overall goal of this study was to assess the psychometric properties items of "natural number bias test". To achieve this goal, a comprehensive test was constructed to test 7 and 9 graders’ natural number bias. This test had 62 tasks which administered on 181 secondary school students at Kerman in a pencil-and-paper form. After of pilot administration of test, data was collected and were analyzed by item response theory modeling. Data analyzing by R software has shown acceptably fitting whit dichotomous rash model. After removing 7 Item, the test had high diagnostic value in its purpose. Results showed that a natural number bias could be found on secondary student in all three aspects. The most difficulty was for "density" items and least difficult was for "size" items. "operations" items were scattered across the Rash scale. Most students were in the top questions test scale. Researchers can choose Items for participants based on their ability.
Asghar Minaei; marzieh hasani
Abstract
The current study aimed to improve precision and item functioning of the OHQ by applying Rasch analysis to a sample of 212 participants. A convenience sample of 212 college students (139 girls and 78 boys) from a number of universities in Tehran city completed the OHQ questionnaire. Data were analyzed ...
Read More
The current study aimed to improve precision and item functioning of the OHQ by applying Rasch analysis to a sample of 212 participants. A convenience sample of 212 college students (139 girls and 78 boys) from a number of universities in Tehran city completed the OHQ questionnaire. Data were analyzed using Rasch analysis approach using RUMM2030 software. Results indicated that a number of the OHQ items displayed disordered thresholds. Therefore, items were rescored in a uniform fashion to correct the thresholds. Furthermore, three items (18, 19, and 25) displayed poor fit to Rasch model and were removed. Best fit to the unidimensional Rasch model was achieved after rescoring items in uniform fashion and removing items number 18, 19 and 25. Using the ordinal-to-interval conversion tables published here, ordinal OHQ scores can now be transformed to interval level data and thus subjected to parametric statistical analysis without violating fundamental assumptions. The precision of the instrument can be improved significantly by these minor modifications without the need to modify the original response format.