Approximation of distribution law of experimental test data to assess reliability of information-measuring and control systems

Methods of approximation for the distribution law of experimental data find wide application in problems of reliability assessment in tests of both hardware and software of software modules of information-measuring and control systems (SM IMCS). Thus, the main task is to solve the problem of increasing the accuracy of the approximation and simplify experimental data processing. In this paper various modification types of Pearson distribution for data taking both positive and negative values, and for data taking only positive values are considered. The described modifications allow one to solve a range of problems related to the existing distributions, as well as to improve the simplicity of the approximation procedure. Pearson logarithmic distributions are proposed for experimental data that take only positive values.