CTT-based education measurement equivalence method and device, server and storage medium

Abstract

The invention discloses a CTT-based educational measurement equivalence method and device, a server and a storage medium, and the method comprises the steps: collecting original test data which comprises test paper questions and test result data of each test, and the test result data comprises score data of each question; summing the calibrated test question difficulty estimation average value, the original test data and the product of the test question score weight to obtain a test paper difficulty parameter; calculating to obtain a sample standard score according to the test paper difficultyparameter, the average score and the standard deviation of each test; and according to a set value range and a conversion formula, performing equivalent processing on all sample scores according to the sample standard score. The invention is efficient, low in cost and convenient to implement, and can be easily understood, mastered and used by various front-line evaluation personnel and testees.

Description

technical field [0001] The present invention relates to the technical field of big data statistics, in particular to a CTT-based educational measurement equivalent method, device, server and storage medium. Background technique [0002] Traditionally, in the field of educational measurement theory, there are two theories: classical measurement theory (CTT) and item response theory (IRT). Traditionally, there have been a large number of practical applications of classical measurement theory, especially in the field of education. A large number of front-line teachers and teaching researchers can basically understand and use most of the concepts and methods that belong to CTT, but in terms of equivalent methods, Several equivalent methods in the traditional classic measurement theory have great constraints and limitations. For example, the equivalent method of anchor questions needs to be implemented based on the construction of a high-standard and high-quality question bank sy...

AI Technical Summary

Problems solved by technology

[0004] One is the complexity of the algorithm model, which greatly increases the cycle cost;

[0005] The second is that the implementation process is extremely complicated, and many methods have repeated iterative processes, and their practicability is limited;

[0006] The third is that its concepts and results are difficult to be understood by front-line teachers and teaching researchers, and even more difficult to be understood by students, parents and society

[0007] Of course, with the development of Computer Adaptive Testing Technology (CAT) based on Item Response Theory (IRT) in recent years, many more mature methods and systems have emerged, but their applicable scenarios are still limited and cannot replace traditional testing methods. exams and assessments

Images