Bauman Moscow State Technical University
Author list of organization
List of articles written by the authors of the organization
-
REAL AND NOMINAL SIGNIFICANCE LEVELS IN STATISTICAL HYPOTHESIS TESTING
01.00.00 Physical-mathematical sciences
DescriptionIn the statistical hypothesis testing, critical values often point to a priori fixed (nominal) significance levels. As such, typically researcher uses the values of three numbers 0.01, 0.05, 0.1, to which may be added a few levels: 0.001, 0.005, 0.02, and others. However, for the statistics with discrete distribution functions, which, in particular, include all nonparametric statistical tests, the real significance levels may be different from the nominal, differ at times. Under the real significance level we refer to the highest possible significance level of discrete statistics, not exceeding a given nominal significance level (ie, the transition to the next highest possible value corresponding discrete statistical significance level is greater than a predetermined nominal). In the article, we have discussed the difference between nominal and real significance levels on the example of nonparametric tests for the homogeneity of two independent samples. We have also studied two-sample Wilcoxon test, the criterion of van der Waerden, Smirnov two-sample two-sided test, sign test, runs test (Wolfowitz) and calculated the real significance levels of the criteria for nominal significance level of 0.05. The study of the power of these statistical tests is accomplished by means of Monte Carlo method. The main conclusion: the use of nominal significance levels instead of real significance levels for discrete statistics is inadmissible for small sample sizes
-
A MODEL OF THE CONFLICT LINGUISTIC PERSONALITY IN EVERYDAY CONFLICT DISCOURSE
10.00.00 Philological sciences
DescriptionThe aim of the study is to describe the concept of conflict linguistic personality and construct a model of linguistic identity. By summing up common features of the individual personalities we have created the model of conflict linguistic personality, based on three levels: verbal-semantic, cognitive and pragmatic. 1. Verbal - semantic level. Unlike other subtypes of conflict discourse, everyday conflict discourse is characterized by slang, invective, obscene vocabulary. Another feature of everyday conflict discourse is familiarity. Imperatives are also among the characteristic features of conflict. There are also some non-verbal components that play an important role in constructing the model of conflict linguistic personality, such as gestures and mimicry. 2. Cognitive level. Typical conflict linguistic personality rarely tries to mince the words at the peak of the conflict, so his/her cultural level comes "through the language." 3. Pragmatic level. On this level diverse and even opposing tactics are possible depending on the purpose of conflict linguistic personality, as well as his/her social role and psychological state at the moment. The cooperative tactics include: acceptance, conviction, compassion, assignment, promise, etc. Noncooperative tactics include: mockery, accusation, insults, threats, pressure, interruption, provocation
-
NON-PARAMETRIC CYCLES ESTIMATORS
01.00.00 Physical-mathematical sciences
DescriptionIn many applications, we study the time series (or a random process), which is the sum of the periodic deterministic function of time and random errors that distort the periodic signal. It is required to estimate the length of the period and the periodic component. It does not assume that the periodic function is included in any parameter family of functions, such as finite sums of sines and cosines. It is obvious that the assumption of occurrence of a periodic function in parametric family does not meet the characteristics of the real world, ie, is conditional, internal mathematical (look for the keys under the lamp because there is a light, not in the bush, where lost, because there are dark). For similar reasons, it is impossible to assume that the distribution function of the random errors is included in any parameter family of distributions. In accordance with the new paradigm of mathematical statistics in this article we studied the problem of nonparametric estimation (minimum) length of the period and the periodic component of the signal. On the basis of natural variation and scope of indicators is suggested a new class of nonparametric estimators of the length of the period and the periodic component in the time series. Based on the general results of statistics of objects of non-numeric nature we proved the consistency of these estimates. From the practical point of view it is necessary to minimize the numerical (one parameter - ability length of period of time) one or more of the 66 functionals, described in the article
-
STATE AND PROSPECTS OF APPLIED AND THEORETICAL STATISTICS
01.00.00 Physical-mathematical sciences
DescriptionThe general scheme of modern statistical science is just like this. Mathematical Statistics is a part of mathematics that studies the statistical structure (it itself does not give recipes analysis of statistical data, however, it is developing methods that are useful for use in theoretical statistics). Theoretical Statistics - the science dedicated to the models and methods of analysis of concrete statistical data. Applied Statistics (in the narrow sense) is devoted to the statistical techniques of data collection and processing (it includes the methodology of statistical methods, the organization of sample surveys, the development of statistical techniques, the creation and use of statistical software). Applications of statistical methods in concrete fields (in economics and management - Econometrics, in biology - Biometrics, in chemistry - Chemometrics, in technical research - Technometric, in geology, demography, sociology, medicine, history, etc.). Often positions 2 and 3 together are called Applied Statistics. Sometimes position 1 is called Theoretical Statistics. These terminological differences are related to the fact that the above-described development of the considered scientific and applied field not once, not completely and not always adequately reflected in the minds of experts. Meanwhile, there are still textbooks of appropriate level of representation of the mid-twentieth century. The article analyzes the post-war development of the national statistics. We have identified five "growth points": nonparametrics, robustness, bootstrap, statistics of interval data, and statistics of non-numeric data. We have discussed content, development and the basic ideas of statistics of nonnumeric data. We have given a number of unresolved problems of theoretical and applied statistics
-
STATISTICAL METHODS IN HISTORY
01.00.00 Physical-mathematical sciences
DescriptionWe have given a critical analysis of statistical models and methods for processing text information in historical records to establish the times when there were certain events, ie, to build science-based chronology. There are three main kinds of sources of knowledge of ancient history: ancient texts, the remains of material culture and traditions. The specific date of the extracted by archaeologists objects in most cases can not be found. The group of Academician A.T. Fomenko has developed and applied new statistical methods for analysis of historical texts (Chronicle), based on the intensive use of computer technology. Two major scientific results were: the majority of historical records that we know now, are duplicated (in particular, chronicles, describing the so-called "Ancient Rome" and "Middle Ages", talking about the same events); the known historical chronicles tell us about real events, separated from the present time for not more than 1000 years. It was found that chronicles describing the history of "ancient times" and "Middle Ages" and the chronicle of Chinese history and the history of various European countries do not talk about different, but about the same events. We have the attempt of a new dating of historical events and restoring the true history of human society based on new data. From the standpoint of statistical methods of historical records and images of their fragments – they are special cases of non-numeric objects of nature. Therefore, developed by the group of A.T. Fomenko computer-statistical methods are the part of non-numerical statistics. We have considered some methods of statistical analysis of chronicles applied by the group of A.T. Fomenko: correlation method of maximums; dynasties method; the method of attenuation frequency; questionnaire method codes. New chronology allows us to understand much of the battle of ideas in modern science and mass consciousness. It becomes clear the root cause of cautious attitude of the West towards Russia
-
Description
The article describes a new approach to the assessment of the economic system. The authors propose to assume that the system grows, if its share in the world production increases. For the qualitative assessment, we have offered to analyze the dynamics of growth of exports of products with high benefit to the foreign countries, which include engineering goods, defense, manufacturing materials. On the world market of hightech products, we have the stiff competition and the growth of exports of domestic products with high benefit indicates high level of innovation. Based on the analysis of available statistical data, we revealed a correlation between exports of innovative products, the volumes of financing research and development and foreign direct investment in the national economy. It was determined foreign capital has a negative impact on exports of products with high benefit. The authors proposed a two-factor regression model, which allows you to make short-term forecasts and allocate resources. The study showed that despite the ongoing economic sanctions and unsuccessful economic reforms in the past, Russia has a high potential for innovation, which is activated when reducing the influence of foreign capital. Attempts to isolate the Russian economic system led to the mobilization of resources and the growth of innovation activity of domestic business
-
FORECAST OF INFORMATION AND COMMUNICATION TECHNOLOGIES
01.00.00 Physical-mathematical sciences
DescriptionForecasting of scientific and technical progress is necessary to make grounded management decisions. In this article, we forecast the development of information and communication technologies in order to solve a particular but important issue of design of professional standards in the aerospace industry. We identify the factors affecting the development of information and communication (computer) technologies, with their help determine the trends of development of these technologies over the next two decades. The main trend - the maximum cheaper production of computer (or network) components, combined with an increase in their capacity. One way to reduce the cost of production is the "centralization" - combining several components into one. The third trend - the desire to reduce the size of computers. The size of a future computer could be a device the size of a pencil, a pin or button, as the system unit has a negligible size, keyboard and display are virtual, transfer any amount of information through a virtual office online. The development of secure free copying will lead to increased use of this free software and technologies "rental program" over the Internet. We predict an increase in reliability and intensive programs while maintaining the general principles of the interface. Revolutionary changes are expected production (machines, sensors), and household appliances
-
LIMIT THEOREMS IN STATISTICAL CONTROL
01.00.00 Physical-mathematical sciences
DescriptionThe article analyzes the development of the theory of statistical control (from the XVIII century to the present). Prof. M.V. Ostrogradskii (1846) clearly describes the practical needs (ie, arising from the quality assurance of large quantities of bags of flour or pieces of cloth), to meet whom he spent his research. At the same time Simpson was among the ideas of probability theory XVIII century. Therefore prof. M.V. Ostrogradskii may be regarded as the founder of the theory of statistical process control (not only in our country but all over the world). Limit theorems of probability theory and mathematical statistics have provided a number of asymptotic results in problems of statistical quality control, offer based on these best practices. However, we must find out how much interest among specialists characteristics are different from limit for finite sample sizes. Such research for the synthesis algorithm control plan on the basis of the limit average output level of defects is made in this article, and for the synthesis algorithm control plan on the basis of the acceptance and the rejection levels of defects - not yet (clarification of the conditions of applicability of this algorithm - unsolved problem of applied mathematics). We have briefly reviewed the development of our researches on the statistical control. Control units can be not only some units of production, but also documents (with internal and external audit), and standard units of air, water and soil in the environmental monitoring. One of the achievements can be regarded as the transfer of statistical control of production for environmental monitoring
-
MODERN ECONOMETRIC METHODS - INTELLECTUAL TOOLS OF ENGINEERS, MANAGERS AND ECONOMISTS
01.00.00 Physical-mathematical sciences
DescriptionStatistical methods are widely used in domestic feasibility studies. However, for most managers, economists and engineers, they are exotic. This is because modern statistical methods are not taught in the universities. We discuss the situation, focusing on the statistical methods for economic and feasibility studies, ie, econometrics. In the world of science, econometrics has a rightful place. There are scientific journals in econometrics, Nobel Prizes in Economics are awarded to series of researches in econometrics. The situation in the field of scientific and practical work and especially the teaching of econometrics in Russia is disadvantaged. Often, individual particular constructions replace econometrics in general, such as those related to regression analysis. In econometrics we select three types of scientific and applied activities: development and study of methods of applied statistics, taking into account the specifics of economic data; development and study of econometric models, in accordance with the specific needs of economic science and practice; the use of econometric methods for statistical analysis of specific economic data. This article describes these three types of scientific and applied activities. We discuss the specificity of economic data. We show the importance of economic non-numeric values. We discuss the statistics of interval data - scientific direction at the joint of metrology and statistics. We give the representation of the econometric models. Problems of application of econometric methods are considered as an example of inflation. We discuss the statistics and econometrics as the field of scientific and practical activities. We have examined econometric methods in practical and training activities
-
THE ASYMPTOTIC INFORMATION CRITERION OF NOISE QUALITY
DescriptionIntuitively everyone understands that noise is a signal in which there no information is, or which in practice fails to reveal the information. More precisely, it is clear that a certain sequence of elements (the number) the more is the noise, the less information is contained in the values of some elements on the values of others. It is even stranger, that noone has suggested the way, but even the idea of measuring the amount of information in some fragments of signal of other fragments and its use as a criterion for assessing the degree of closeness of the signal to the noise. The authors propose the asymptotic information criterion of the quality of noise, and the method, technology and methodology of its application in practice. As a method of application of the asymptotic information criterion of noise quality, we offer, in practice, the automated systemcognitive analysis (ASC-analysis), and as a technology and software tools of ASC-analysis we offer the universal cognitive analytical system called "Eidos". As a method, we propose a technique of creating applications in the system, as well as their use for solving problems of identification, prediction, decision making and research the subject area by examining its model. We present an illustrative numerical example showing the ideas presented and demonstrating the efficiency of the proposed asymptotic information criterion of the quality of the noise, and the method, technology and methodology of its application in practice