Scientific Journal of KubSAU

We have proposed the method for testing of independence of two alternative variables on the basis of statistics of non-numeric data. The method is aimed at application in problems of statistical quality control. Testing of independence is based on set of small samples, i.e., in the Kolmogorov’s asymptotics, when the number of unknown parameters of the distribution increases in proportion to the data size

The purpose of the article - to justify the need to develop the methodology of statistical methods as an independent scientific direction. The models of mathematician and applied specialist are presented. We have obtained the conclusions on teaching and research and discussed five major unsolved problems of statistical methods: the effect of deviations from the traditional prerequisites; use asymptotic results for finite sample sizes; selecting one of the many specific tests for the hypothesis; organization of theoretical work in the field of statistical methods; conduct applied research and teaching of statistical methods

It was established that the two-sample Wilcoxon test (Mann-Whitney test) was designed to test the hypothesis H0: P(X

On the basis of a new paradigm of applied mathematical statistics, data analysis and economic-mathematical methods are identified; we have also discussed five topical areas in which modern applied statistics is developing as well as the other statistical methods, i.e. five "growth points" – nonparametric statistics, robustness, computer-statistical methods, statistics of interval data, statistics of non-numeric data

We have analyzed the current state of the main computer-statistical methods, identified achievements and existing problems, outlined the prospects of further movement and formulated the problems to be solved. We have also discussed the Monte Carlo methods, pseudo-random numbers, simulation, bootstrap and resampling, the automated system-cognitive analysis. We have considered the applications of computer statistics in controlling and properties of statistical packages as the tools for researchers

We have allocated the basic sources of uncertainty in various industrial and economic situations. We have also considered the role and the tasks of forecasting in the management of industrial companies, particularly in the rocket and space industry. We have discussed the methods of organizational and economic forecasting - statistical, expert, combined, including foresight and given some suggestions for improving the forecasting and planning mechanisms for practical use when creating space systems

Statistical control is a sampling control based on the probability theory and mathematical statistics. The article presents the development of the methods of statistical control in our country. It discussed the basics of the theory of statistical control – the plans of statistical control and their operational characteristics, the risks of the supplier and the consumer, the acceptance level of defectiveness and the rejection level of defectiveness. We have obtained the asymptotic method of synthesis of control plans based on the limit average output level of defectiveness. We have also developed the asymptotic theory of single sampling plans and formulated some unsolved mathematical problems of the theory of statistical control

In accordance with the new paradigm of mathematical statistics the statistics of objects of nonnumerical nature (statistics of nonnumerical objects, non-numerical data statistics, non-numeric statistics) is one of the four main areas of mathematical statistics. Statistics of objects of nonnumerical nature consists of a central core - statistics in spaces of arbitrary nature - and statistical theories of analysis of specific types of non-numeric data. To identify possibilities of application of statistics of objects of nonnumerical nature it is useful to explore the multiformity of objects of non-numeric nature. This is the subject of this article. We have considered the results of measurements at scales other than absolute; binary relations; dichotomous (binary) data; sets. We have also analyzed the objects of non-numerical nature as statistical data, and their importance in the formation of statistical or mathematical model of a real phenomenon, as a result of data analysis

One of the important problems of marketing - the choice moments of output of new models (brands) of products to the market. In the article for the first time in scientific periodicals we have proposed a sketch economic-mathematical optimization model for selection of time of output of new brands to market. We have received the calculation formulas for the moments of the output of new brands

For the first time we have developed a general additive-multiplicative model of the risk estimation (to estimate the probabilities of risk events). In the two-level system in the lower level the risk estimates are combined additively, on the top – in a multiplicative way. Additive-multiplicative model was used for risk estimation for (1) implementation of innovative projects at universities (with external partners), (2) the production of new innovative products, (3) the projects for creation of rocket and space equipmen