Computerized testing is widely used for diagnostics and estimation of professional skills including education quality control. Both quality of testing and reliability of its results depend on a selected test technology that was a scientific research object during last years. Initially specialists applied the classical theory borrowed from physics for test design basing on the suggestion that measured characteristics have true mean distorted by some system errors. This approach was widely used but it had many disadvantages. In 1960 G. Rash proposed the new one-parametric model for optimal test design, according to which probability of the right answer to a test question depends on the distance between person skill level and the difficulty of introduced test tasks. Some problems of such models are: - Ignoring the fact that the person tired of the testing process could cause essential changes in test results - Time spent on solving tasks has no influence on skill estimation - A subject needs to solve rather great number of test tasks to get sufficient accuracy of skill estimation Difficulty of calculating probability distributions of possible test results that is necessary for evaluating their reliability - The employed procedure of result accuracy estimation with the aid of the maximum likelihood method is comparatively difficult for practical implementation. These problems inspired creation of the adaptive testing technology under consideration, which is based on application of trained structures in the form of discrete-and continuous-time Markov models. Its peculiarities, in particular, are revealing and using test solution capability changes in quantitative evaluation of their time-domain dynamics as well as taking into account timetable of testing process. The approach suggested has certain advantages over the testing techniques, which were used before, owing to its greater information capability and acceleration of a test procedure.
