кластерный анализ
The Statistical Analysis of Differentiation of The Post-Soviet Countries During Transformation of Economy |
Introduction. Process of transition of fifteen countries of ex-member of the USSR from planned economy to market, was followed by basic changes in political, economic and social life of society. Various approaches to the undertaken reforms, and opposite strategic objectives, cause the distinctions of economies of the Post-Soviet countries observed now. Theoretical analysis. Works of many domestic scientists are devoted to a problem of the analysis of results of the period of transition of the Post-Soviet countries to market economy, they divide set of the Post-Soviet countries on the basis of various grouping signs, but along with advantages of these researches it is necessary to point to one essential shortcoming contributing a subjectivity share in the received results, it is high-quality approach to formation of groups. It causes need of application of quantitative approach and first of all multidimensional group. Empirical analysis. As a result of application to fifteen Post-Soviet countries of multidimensional group (more precisely than the cluster analysis) it has been established that in entire four reference periods (1991, 1999, 2009, 2015) three groups are allocated, at the same time in the last three periods a ratio and fullness of groups it is identical that points to stabilization of set. The first group had included the countries with impressive natural and human resources, the second the republics which have changed polarity from Russia with the European Union, the USA and China. The third group is formed by the Baltic States which were a part of the European Union and at the expense of it have considerably increased a separation from other Post-Soviet countries that is substantially shown in such indicator as GDP per capita. Conclution. Quarter of the century of development of the Post-Soviet countries out of the Soviet Union was led to their considerable deformation on the level of political and social and economic development. The republics which had good positions on the natural and human capital at the beginning of transition that it has allowed them to be integrated into global economy have achieved considerable progress. The Baltic States which were a part of the European Union and substantially, the improved macroeconomic indicators are also obviously allocated. |
IZVESTIYA OF SARATOV UNIVERSITY. NEW SERIES. SERIES: ECONOMICS. MANAGEMENT. LAW. 2018. vol. 18, iss. 3 |
Econometric Modeling Studio Price Method of Geographically Weighted Regression |
Introduction. Detection and measurement of interdependencies in the housing market is one of the key issues examined econometric methods. Compared with traditional methods of geographically weighted regression extends the understanding of how the units belonging to the set of specific geographical coordinates affect the relationship between the covariates and the price of real estate. In this regard, the aim of this study was to analyze the spatial differences in the price of one-bedroom apartments presented in the secondary housing market of Orenburg. Methods. We used the method of cluster analysis, graphical method, analysis of variance, the classical regression model and geographically weighted regression. Results. Parameter estimation of the global (general) model by least squares and geographically weighted regression, has shown that SMT has a better fit, and is proof of the spatial differentiation of the regression coefficients. Conclusions. When modeling the price one-room apartment to be preferred geographically weighted regression, since it is estimated regression coefficients for each object combination and therefore recognized geographic differences in the dependencies, it is difficult to display the total regression equation. |
Известия Саратовского университета. Новая серия. Серия Экономика. Управление. Право. 2015. Т. 15, вып. 4 |
Factors Convergence Russian Regions and Their Characteristics in the Reproductive Cycle of the Human Potential |
Introduction. Search the development of the Russian economy is characterized by increasingly complex social and economic phenomena, differentiation and specialization of regions of Russia, accompanied by a steady increase in the number of factors that significantly determine the scope, pace and quality of economic growth. According to the concept of long-term socio-economic development of the Russian Federation for the period up to 2020. One of these factors is the human potential. Empirical results. The article simulated beta convergence in terms of «actual final consumption of households per capita» for the 2002–2012 biennium. Identified key factors for the reproduction of human potential in the Russian regions on the basis of the principal components method. Held clustering that refines the types of regions, which compares the level and dynamics parameters of reproduction of human potential, as well as regional variations, indicating the convergence process. |
Номер журнала 586 |
ПРИМЕНЕНИЕ МЕТОДОВ КЛАСТЕРНОГО АНАЛИЗА ДЛЯ ОЦЕНКИ СХОЖЕСТИ СЛЕДОВ БОЙКОВ |
Введение. Одной из важнейших задач судебно-баллистической экспертизы является идентификация оружия по следам бойка. Данная задача обычно связана с поиском совпадающих (парных) следов по большим базам данных. Для этого широко используются баллистические идентификационные системы, такие как ПОИСК, ТАИС, Арсенал и другие, в которых исполь- зуются автоматические алгоритмы поиска парных следов, основанные на подсчете функции взаимной кросс-корреляции. В данной работе предложен иной подход, разработанный для изображений следов бойков, содержащих признаки в виде крупных областей неопределенной формы. К ним применялись методы кластерного анализа для формирования приоритетного списка. Теоретическая часть. В теоретической части дается алгоритм выделения и сравнения дескрипторов – характеристик, описывающих изображения следа бойка. После чего предложен способ формирования приоритетного списка, анализируя который, эксперт сможет сделать вывод о парности следов. Экспериментальная часть. Разработанный алгоритм был применен к базе данных, состоящей из более чем 100 изображений следов бойков 24 экземпляров оружия. Заключение. Разработанный алгоритм позволяет формировать приоритетный список из 20 изображений, в который входят парные следы (если такие имеются в электронной базе данных) с вероятностью 100%. Таким образом, предложенная методика позволяет существенно сократить время поиска следов. Данный алгоритм осуществляет предварительную фильтрацию и позволяет выделить список следов, к которым имеет смысл применять более сложные критерии, такие как сравнение контуров, особых точек изображений и т.п. |
Номер журнала 371 |