Assigning observations to highly separable although relatively homogeneous groups is still a challenging task despite the abundance of well-elaborated theories and effective, practical algorithms. Not just the aim of clustering then the underlying data itself influences the choice of method and the way of assessing the results. Outliers and non-normal data distribution can lead to surprising, unstable and many times undesirable clustering results especially in higher dimensions. This implies the importance of some human supervision in case of such unsupervised algorithms as well. In this paper a robust clustering alternative is presented based on the Most Frequent Value Method for crisp-type clustering in case of real-life data. The proposed approach is compared with the k-Medians algorithm. A favourable attribute of the applied procedure is its ease of application on multidimensional data sets where critical judgment of formed groups is particularly troublesome.

Identification of the strength of relationship between two variables is usually done by the investigation of their correlation coefficient. For determining the strength of linear relationships usually Pearson’s correlation coefficient is used that requires the variables to be normally distributed. However, presence of outliers and even minor deviations in the underlying distribution from the Gaussian can lead researchers and practitioners astray when interpreting the results. Since detection of multidimensional outliers is not always feasible and our data sample does not necessarily shows normal distribution in practice and furthermore correlation analysis is a fundamental step for selecting variables for various statistical analysis a robustified correlation measure is advised to be calculated alongside conventional Pearson’s correlation coefficient. In this study we apply the Most Frequent Value (MFV) robustified correlation coefficient for investigating the speed of convergence in economic growth among NUTS regions of the European Union, where from theory linear relationship is assumed but the corresponding available data are not normally distributed and may contain outliers.

The objective of this research is to present a qualitative methodology for the empirical investigation of enterprises’ responses to economic shocks. Annual balance sheets and income statements of nearly 26,000 Hungarian small- and medium-sized enterprises (SMEs) in the production sector have been examined. A data-driven resilience metric is introduced, based on annual sales growth fluctuations in response to idiosyncratic economic disturbances. Accordingly, Logistic Regression and Random Forest classification of company-year observations have been conducted. Non-parametric statistical tests based on pair-matching suggest that while resilience against economic downturns is critical for short-term survival, it does not necessarily translate to any enhanced long-term development or prosperity. This study demonstrates that companies exposed to economic setbacks tend to lag behind compared to control pairs and illuminate the aftermath of resilient shock reactions at the population level. Our findings suggest that enterprises that have experienced an economic shock should be considered vulnerable and monitored regardless of their shock reaction history as part of a sustainable national economic strategy to foster overall competitiveness and productivity and maintain supply chains.

In a globalized market environment with continuously changing conditions and customer requirements, international and cross-border co-operations gain an increasing importance for different actors in order to establish adequate networks. This can highly contribute to the sustainable, more effective operation of market actors in the long-run that can even become more resilient in case of turbulent events. 51 actors of the Central European region with different organisational types were selected and their preferences were asked in a survey about their interests regarding up-to-date technologies in which they would like to work together with other partners and they were ready to broaden the limits of their present knowledge. In this paper, based on the received answers a clustering of the members is performed with the K-modes algorithm and a well-interpretable profiling of the resulted groups is provided, which may serve as a tool to assist more beneficial network formations within the Central European region.