Structuring Multidimensional Data in the Study of the Development of Information Society in Russian Regions

• Main Authors: N. M. Gabdullin, I. A. Kirshin
• Format: Article
• Language: Russian
• Published: Government of the Russian Federation, Financial University 2019-12-01
• Series: Мир новой экономики
• Subjects: big data; data structure analysis; economy digitalisation; clustering; principal components method; information and communication technologies
• Online Access: https://wne.fa.ru/jour/article/view/241
• ISSN: 2220-6469; 2220-7872

In the article, the authors present the results of the analysis of the structure of multidimensional data on the factors of use of information and communication technologies (ICT) for the development of the information society in the Russian Federation. We chose the subjects of the Russian Federation as the objects of observations, and the average annual values of the corresponding factors of monitoring the development of the information society in the Russian Federation for the period from 2010 to 2017 as the factors of each object of observations. The study was carried out to reduce the set of factors of ICT use in the subjects of the Russian Federation and identify their structure. The analysis of the structure of factors is carried out by applying the Principal Component Analysis (PCA) method, implemented by the authors in the integrated development environment Rstudio. Through the use of the PCA method, we identified the structure of the initial factors of ICT use for the development of the information society in the Russian Federation and made their reduction. Then, we showed that the identified factor loads have specific semantic interpretations that consolidate the links of individual factors of ICT use for the development of the information society in the Russian Federation. The factor analysis carried out by us proves the effectiveness of the DCA method in research on the development of digitalisation of the regions of the Russian Federation for structuring the initial data and qualitative interpretation of the results. We have proved that factor loadings revealed employing the application of a method of RSA have the deterministic economic sense.