Abstract

The aim of the article is to identify the homogeneity of the regions of Ukraine, as the objects of the anti-crisis management system by methods of cluster analysis. The results of the analysis. To determine the regional disparities in socio-economic development of the regions of Ukraine the grouping of the regions has been carried out by methods of cluster analysis that has enabled to identify the homogeneity of the objects (regions) of the anti-crisis management system. The output data are materials of the State Statistics Service of Ukraine on socio-economic situation of the Ukrainian regions in 2015. In order to determine the number of clusters for a given summation of objects the index of entropy has been calculated for each possible grouping. The best variant is considered the variant by which the deviation of the actual entropy index from its maximum value is minimal. The results of the held calculations have shown that the smallest deviation of the entropy index from the maximum possible of its value is observed on grouping the objects into three clusters ∆N = 0,75%. Therefore, the regions of Ukraine according to the indexes of socio-economic development have been grouped into three clusters (by k-medium method). After clustering by k-medium method it has been determined that nine regions of Ukraine must be referred to the first cluster (Vinnytsia, Kirovohrad, Mykolaiv, Poltava, Sumy, Kherson, Khmelnytskyi, Cherkasy and Chernihiv); to the second – eight regions (Volyn, Zhytomyr, Ivano-Frankivsk, Luhansk, Rivne, Ternopil, Chernivtsi), to the third – seven regions (Dnipropetrovsk, Donetsk, Zaporizhzhia, Kyiv, Lviv, Odesa, Kharkiv). The results of the discriminant analysis that has been carried out to verify the quality of the classification, have confirmed the correctness of the classification that is evidenced by the value of lambda Wilks, the results of the matrix classification, the results of canonical analysis. Based on the results of cluster and canonical analysis the conclusion is made about the heterogeneity of the regions of Ukraine from the point of view of their socio-economic development. Generalization of the differences has enabled to characterize the clusters: the third cluster has the best indexes. Its specific weight in the structure is 29%. Almost all of its indicators are characterized by the highest values except the volume of agricultural production. The scientific novelty of the research is to apply methods of multivariate statistics to research and develop the system of anti-crisis management. The practical significance of the study results is in the conclusions of homogeneity within the respective cluster that enables to develop and implement an effective system of anti-crisis management. Conclusions and directions of further researches. As a result of the held clustering of the regions in Ukraine by the indicators of socio-economic development of regions the homogeneity of the regions within the respective clusters is identified that enabled to identify three clusters. The received clusters have enabled to develop the anti-crisis management system for the regions according to their belonging to a particular cluster. The correctness of the observation classification by k-method is confirmed by the results of the discriminant analysis. The generalization of the differences has enabled to characterize the identified clusters, but it is difficult to carry out the identification of the region’s belonging to a particular cluster for the next period according to the received results of the research. That is why it is planned to develop mathematical functions for each cluster (discriminant function) and carry out the component analysis that will enable to determine the factor features and their components. In addition, it is planned to develop the classification of industries according to the availability level of crisis events. Based on this research and the planned one, the identification matrix of the crisis of the companies will be developed that will enable to develop a strategy for anti-crisis management: crisis prevention, the reduction of the crisis impact and the elimination of the consequences.

Keywords: anti-crisis management, cluster analysis, cluster, region, discriminant analysis

JEL Classification: C38, H12, O18.

Cite as: Ivanova, N. (2017). Identification of homogeneity of objects of anti-crisis management systen by cluster method. Marketing and Management of Innovations, 4, 188-198. https://doi.org/10.21272/mmi.2017.4-16

This work is licensed under a Creative Commons Attribution 4.0 International License

References

1. Hriaznova, A.H. (Eds.). (1999) Antikrizisnyi menedzhment [Crisis management]. Moscow: Assotsiatsiia avtorov i izdatelei «Tandem» ; Izdatelstvo Ekmos [in Russian].
2. Blank, I.A. (2005). Finansovyi menedzhment [Financial management]. Kyiv: Elha; Nika-Tsentr [in Russian].
3. Borovikov, V.P. (2003). Statistika. Iskusstvo analiza dannykh na komputere [Statistica. Art computer data analysis]. Saint Petersburg : Piter [in Russian].
4. Hazarian, S.V. (2013). Teoretychni osnovy antykryzovoho upravlinnia v rehioni [Theoretical basis of anti-crisis management in the region]. Publichne upravlinnia – Public management, 2, 56-61 [in Ukrainian].
5. Haivoronska, Yu.Ye. (2006). Metodychni osnovy funktsionuvannia mekhanizmu antykryzovoho upravlinnia pidpryiemstvom [Methodical basis of a mechanism of anticrisis management]. Candidate’s thesis. Kyiv: National transport University [in Ukrainian].
6. Holiyad, N.Yu. (2005). Modeli antykryzovoho upravlinnia rehionom [Model of crisis management of the region]. Extended abstract of candidate’s thesis. Kharkov: HNEU [in Ukrainian].
7. Horbenko, R.O. (2008). Udoskonalennia sposobiv otsiniuvannia konkurentospromozhnosti mashynobudivnoho pidpryiemstva [Improving methods of evaluating the competitiveness of machine-building enterprise]. Extended abstract of candidate’s thesis. Luhansk: Volodymyr Dahl East Ukrainian National University [in Ukrainian].
8. Sait Derzhavnoi sluzhby statystyky Ukrainy [Site of State Statistics Service of Ukraine]. ukrstat.gov.ua. Retrieved from http://www.ukrstat.gov.ua [in Ukrainian].
9. Diuran, B., & Odell, P. (1977). Klasternyi analiz [Cluster analysis]. Moscow: Statistika [in Russian].
10. Yerina, A.M. (2001). Statystychne modeliuvannia ta prohnozuvannia [Statistical design and prognostication]. Kyiv: KNEU [in Ukrainian].
11. Kamneva, A.V. (2014). Doslidzhennia isnuiuchykh instrumentiv ta modelei antykryzovoho upravlinnia na pidpryiemstvi [A study of existing tools and models of crisis management in the enterprise]. Ekonomika ta upravlinnia pidpryiemstvamy mashynobudivnoi haluzi – Economics and management of enterprises of engineering industry, 4, 15-27 [in Ukrainian].
12. Sait Ministerstva ekonomichnoho rozvytku i torhivli Ukrainy [Site of Ministry of Economic Development and Trade of Ukraine]. me.gov.ua. Retrieved from http://me.gov.ua/ [in Ukrainian].
13. Prykhodchenko, T.A. (2016). Antykryzove upravlinnia rehionalnym rozvytkom Ukrainy [Crisis management the regional development of Ukraine]. Stratehiia ekonomichnoho rozvytku Ukrainy – Economic Development Strategy for Ukraine, 39, 118-126 [in Ukrainian].
14. Rehiony Ukrainy u 2016 rotsi: statystychnyj zbirnyk [Regions of Ukraine in 2016: Statistical Yearbook]. (2016). Kyiv: Derzhavna sluzhba statystyky Ukrainy [in Ukrainian].
15. Yahlom, A.M., & Yahlom, I.M. (1973). Veroiatnost i informatsiia [Probability and information]. Moscow: Nauka [in Russian].
16. Altman, E.I., & Rijken, H.A. (2011). Toward a Bottom-Up Approach to Assessing Sovereign Default Risk. Journal of Applied Corporate Finance, 23(1), 20-31.
17. Beaver, W. (1966). Financial Ratios as Predictors of Failure. Journal of Accounting Research, 4, 71-102 [in English].
18. Booth, S. (1993). Crisis management strategy, competition and changes in modern enterprises. New York: Routledge.
19. Hart, P., Heyse, L., & Boin, A. (2001). New trends in crisis management and crisis management research: Setting the agenda. Journal of Contingencies and Crisis Management, 9(4), 181-188. 
20. Porter, M.E. (2003). The economic performance of regions. Regional Studies, 37, 549-578.