Kushnir O. K., Candidate of Economic Sciences, Associate Professor, Associate Professor of the Department of Economics of Enterprise, Kamianets-Podilskyi Ivan Ohiienko National University, Kamianets-Podilskyi, Ukraine

ORCID ID: 0000-0003-2679-2782
e-mail: oksana.kushnir@kpnu.edu.ua

Chaplinsky V. R., Candidate of Economic Sciences, Senior Lecturer of the Department of Economics of Enterprise, Kamianets-Podilskyi Ivan Ohiienko National University, Kamianets-Podilskyi, Ukraine

ORCID ID: 0000-0002-3209-1475
e-mail: chaplinskyi.vadym@kpnu.edu.ua

Statistical Methods for Big Data Analysis

Abstract. Introduction. Big data has been in the spotlight since its inception as organizations understand its importance and use it in their business. The adoption of big data helps businesses discover new opportunities and improve efficiency, which helps increase profits by attracting more customers. In today’s world, the concept of big data is considered the most important for the following reasons: Cost reduction – big data technologies are more cost-effective. And it is the best tool for storing large amounts of data at a lower cost; Fast decision making. With in-memory analytics and the ability to analyze new data sources, big data helps companies analyze data and information faster than ever before.

Purpose. Analyze the features of statistical methods of big data analysis with the growing importance of the features of big data presentation technologies.

Results. It has been established that the existing approaches and methods of information analysis no longer fully fulfill their functions and are becoming less relevant, therefore there is a need to find new opportunities. The diversity of big data requires new statistical ideas and methods that focus on adapting standard statistical models to big data, the size of which exceeds the capacity of a single computer due to its large volume and high speed. The use of statistical analysis methods is proposed, which involve the collection, organization and analysis of data based on established principles to identify patterns and trends and perform several functions: forecasting, modeling, creating models, reducing risk and identifying trends. Statistical analysis will allow you to draw conclusions from the data. Learns the statistical analysis techniques used to analyze the evidence for one’s hypotheses to help businesses make predictions and make decisions about their products and services; get accurate information from numerical data. Statistical methods are used to identify patterns and correlations created by data analysis and attempt to confirm using rigorous scientific methodologies.

Conclusions. It has been proven that the use of statistical methods for the analysis of big data requires the development of a fundamentally new policy regarding information management, its protection, relations with respondents, and the process of training specialists.

Keywords: big data; big data analysis; statistical methods; regression; mean; sample; hypothesis.

References:

1. Bakhrushyn, V. E. (2011). Metody analizu danykh : navchal’nyj posibnyk dlia studentiv. Zaporizhzhia : KPU [in Ukrainian].
2. Cyfrova transformacija ekonomiky : mikro- ta makroaspekty : kolektyvna monoghrafija. (2022). Chernivtsi : Chernivec. nac. un-t im. Ju. Fedjkovycha [in Ukrainian].
3. Big data market size revenue forecast worldwide from 2011 to 2027. Retrieved from https://www.statista.com/statistics/254266/global-big-data-market-forec ast/.
4. Veres, O. M., Olyvko, R. M. (2017). Classification of big data analysis methods. Visnyk Natsional’noho universytetu «L’vivs’ka politekhnika», 872, 84-92 [in Ukrainian].
5. Chaplins’kyj, V. R., Kushnir, O. K., Svider, O. P. (2021). Analysis of big data and its visualization for business needs. Efektyvna ekonomika, 6. Retrieved from http : //www.economy.nayka.com.ua/?op=1&z=8979 [in Ukrainian].
6. Wang, C., Chen, M. H., Schifano, E., Wu, J., Yan, J. (2016). Statistical methods and computing for big data. Stat Interface, 9(4): 399-414, doi: 10.4310/SII.2016.v9.n4.a1.
7. Kampakis, S. (2020). The Decision Maker’s Handbook to Data Science: A Guide for Non-Technical Executives, Managers, and Founders. London, UK. Retrieved from https : //doi.org/10.1007/978-1-4842-5494-3.
8. Beyer, M., Laney, D. (2012). The Importance of Big Data: A Definition. Gartner Inc. Electronic data. Stamford : Gartner, Retrieved from URL : https://www.gartner.com/en/documents/2057415.
9. The Difference Between Data Analytics and Statistics. Retrieved from https://www.rudderstack.com/learn/data-analytics/the-difference-between-data-analytics-and-statistics/.
10. Osaulenko, O. H., Horobets’, O. O. (2022). Problems and prospects of implementation of big data in the official statistics of Ukraine in the conditions of martial law. Suchasna statystyka: problemy ta perspektyvy rozvytku: materialy XX Mizhnar. nauk.-prakt. konf. Kyiv : «Informacijno-analitychne aghentstvo», 26-31 [in Ukrainian].
11. Korepanov, O. S. (2018). Using «big data» for statistical management of the development of «smart» sustainable cities. BiznesІnform, 6, 356-361 [in Ukrainian].