Współczesne zmiany narzędzi badań statystycznych
Contemporary Changes in Statistical Research

Summary/Abstract: Many changes are observed in statistical tools for research in the field of analysis and the forecasting of socio-economic processes. The starting point of the considerations carried out is a classic scheme of statistical investigations in the economic sciences. Particular attention is paid to its limitations. Modern methods of data analysis, based on artificial intelligence, can help eliminate the limitations of the classical statistical investigations. These methods can be counted among supervised learning procedures. The paper next goes on to discuss the basic methods of data classification, including LDA and logit. Supervised learning methods that may have wider application in socio-economic studies are then presented. These include: the Naïve Bayes Classifier, Bayesian Networks, k-nearest neighbours, vector support machines, kernel classifiers, artificial neural networks, decision trees, and a multi-model approach (random forests, bagging, boosting). However, these methods are also subject to certain restrictions. The article is an overview and contains references to works in which supervised learning methods have been applied in socio-economic studies.

• Details
• Contents