The article presents an analysis of the performance of regional governments - the institutions representing the self-governing regions in the Czech Republic. The authors try to answer the question of whether regional governments function similarly or whether they vary in terms of performance, and if they do vary, how structured and how large are these differences. After a review of the position occupied by the regions in the Czech public administration system, and after assessing the ways in which regional government performance can be understood and measured and the accessibility of necessary data, indicators are proposed and used to create an aggregate index of regional government performance. An analysis based on these indicators shows that there are considerable differences between regional governments in terms of the structure and the level of their performance. Based on the performance index it was possible to distinguish regions with above-average, average, and below-average regional government performance. The territorial distribution of these groups and some other factors confirm the validity of these measurements.
Performance evaluation of classifiers is a crucial step for selecting the best classifier or the best set of parameters for a classifier. Receiver Operating Characteristic (ROC) curves and Area Under the ROC Curve (AUC) are widely used to analyse performance of a classifier. However, the approach does not take into account that misclassification for different classes might have more or less serious consequences. On the other hand, it is often difficult to specify exactly the consequences or costs of misclassifications. This paper is devoted to Relative Cost Curves (RCC) - a graphical technique for visualising the performance of binary classifiers over the full range of possible relative misclassification costs. This curve provides helpful information to choose the best set of classifiers or to estimate misclassification costs if those are not known precisely. In this paper, the concept of Area Above the RCC (AAC) is introduced, a scalar measure of classifier performance under unequal misclassification costs problem. We also extend RCC to multicategory problems when misclassification costs depend only on the true class.