Application and interpretation of basic component analysis and regression analysis on educational data on the R program

A person is in a decision-making process at every moment of his life. There are many reasons for the decisions we make, the paths we choose. But we all know that among dozens of reasons, some are more important than others and they shape our thoughts the most. By knowing this, the human brain needs to process information with the same logic. Information continues to accumulate in a cumulative manner and is becoming more chaotic day by day. With the development of technology, the existence of multidimensional data in our lives is an incontrovertible fact. Although it has become quite easy to reach this big data today, processing this data we have reached has become a much more complex process. Especially in recent years, the increasing interest in education methods and researching the reasons for educational success all over the world has caused an increase in the knowledge obtained at the same rate. One of the focal points of scientific research is data and the correct processing and analysis of this data. Data analysis processes bring some difficulties, especially in multidimensional data. One of the focal points of scientific research is data and the correct processing and analysis of this data. Data analysis processes bring some difficulties, especially in multidimensional data. The size of the data, storage difficulties, descriptive statistics, regression, correlation and all similar operations are included in the data analysis process. The Program for International Student Assessment (PISA), which was first implemented by the Organization for Economic Cooperation and Development (OECD) in 1997, in order to compare educational methods and achievements internationally, tests the success of fifteen-year-old students every three years. This comparison brings to mind the question of which factors are more effective in educational success. PISA (Programme for International Student Assessment) is a large-scale exam that collects data on many variables. Thanks to this exam, applied at an international level, it is possible to access not only the exam score, but also data on the factors that may affect the exam score. In this thesis study, it was aimed to determine the most effective variable on the scores obtained by processing the PISA 2018 exam scores and the data of different variables of that period on the R program with the Principal Components analysis and regression analysis method, which are the most used dimension reduction and interpretation methods when working with big data. Keywords: PISA 2018, R Program, Principal Component Analysis, Regression Analysis