Technological advancement across human activities has brought about accelerated generation of huge amounts of data. Consequently, researchers are faced with the problem how to determine adequate ways of turning the available data mass into useful knowledge. Data analysis adapted to these changes when data mining was developed as an approach to data analysis from different perspectives which reveals significant hidden regularities. This paper presents conceptual characteristics of decision tree, an important data mining method which is, due to its explorative nature, exceptionally suitable for detection of data structure when analysing various problem situations. The empirical section of the paper demonstrates applicative characteristics of this method using CHAID algorithm in leadership studies: an interdependence of selected personal characteristics and the manager’s leadership style has been investigated. The aim of the paper is to develop a classification model for identification of the dominant leadership style. The study was conducted on the sample of 417 managers of privately owned small-sized enterprises in Serbia, using a specially designed questionnaire. The classification model identified the set of six statistically significant personal characteristics as predictors of dominant leadership style.

The objective of this study is to explore the role and relevance of leaders’ gender in their choice of dominant leadership style in Serbian companies and institutions. The categories we use in our research are based on the two most popular classifications of leadership styles, established in Iowa and Ohio studies (which identified authoritarian, democratic and laissez-faire style and task-oriented or relationship-oriented leadership style respectively). For data collection we used a 31-statement questionnaire, applying the method of proportional stratified random sampling. The sample contained responses of 79 randomly selected respondents (leaders) from randomly selected organizations in Serbia. To determine whether there is statistically significant dependence between the identified dominant leadership styles and leaders’ gender we applied the Chi-square test of independence as a quantitative statistical method. Our results confirmed statistically significant interdependence between the observed pairs of categorical variables. More precisely, they indicated that female leaders incline towards task-oriented and authoritarian leadership styles, while male leaders prefer relationship-oriented and democratic styles.

Starting from the fact that pronounced differences in the level of development of regions within a particular country can have a serious and significant (negative) impact on its socio-political stability, as well as the performance of the national economy as a whole, it is very important to create conditions for ensuring balanced and sustainable regional development. Due to its pronounced multidimensional nature, the analysis of regional economic disparities is a very complex and statistically demanding task. In this paper, a multivariate methodological framework for the classification of districts in Serbia according to the achieved level of economic development, into internally-homogeneous / externally-heterogeneous groups, based primarily on the application of hierarchical agglomerative clustering procedure and examination of interdependencies between five selected relevant economic indicators, is presented. The statistical validity of the obtained "optimal" classification of districts is additionally tested and confirmed with the results of one-factor multivariate analysis of variance. The resulting categorization clearly and unequivocally confirms the presence of pronounced inequalities regarding the achieved level of economic development between NUTS 3 level territorial units in Serbia, and the existence of regional economic polarization, primarily in direction "developed north – undeveloped south".

No abstract

The aim of the paper is to analyze relationship between Fiat