Využití veřejně dostupných datových souborů ve statistické analýze

The continuously growing number of publicly available data sources represents a significant advantage when selecting datasets suitable for the demonstration of statistical analyses. This bachelor’s thesis focuses on the use of publicly available datasets in the teaching of statistics courses. The main goal of the thesis is to identify and categorize datasets that are appropriate for demonstrating specific statistical methods. The theoretical part of the thesis describes publicly available data sources and statistical methods, including statistical hypotheses, assumptions, and mathematical relationships. The practical part focuses on the application of selected statistical analyses – analysis of variance, contingency tables and regression analysis. These analyses are performed using a combination of statistical softwares, specifically MS Excel and Statgraphics. The results are complemented by interpretations of the outputs. Finally, recommendations are made for the use of datasets that are suitable for demonstrating the mentioned statistical methods. This is a valuable contribution for students as well as educators looking for datasets that support the development of practical skills.