Examination of International Pisa Test Results with Artificial Neural Networks and Regression Methods
Year: 2018
Type: article
Abstract: It is approved that artificial neural networks are considerably effective in analyzing flows in which traditional methods and statics are inadequate to solve. In this article, we use a two-layer feedforward network with tan-sigmoid transmission function in input and output layers with PISA of Turkey and Organisation for Economic Cooperation and Development (OECD) science level values. OECD Programme for International Student Assessment (PISA) surveys reading, mathematical and scientific literacy levels every three years. The PISA assessment works on young people’s ability to apply their knowledge and skills to real-life problems and situations rather than on how much curriculum-based knowledge they have. Assessments are made on three core fields reading literacy, mathematical literacy and scientific literacy. The conclusion is that PISA is an important global benchmarking tool, but that bureaucrats and the media need to use the rich data that have been collected together with information about their academic performance. According to statistical evaluations, regression value of ANN was higher than value of regression methods.Keywords: PISA, Artificial Neural Networks, Regression Methods.
Source: Savunma Bilimleri Dergisi
Authors: Semra Benzer, Recep Benzer
Language: English
Field: Social Sciences
Domain: Social Sciences
SDG: Quality education
Open Access status: bronze
OpenAlex ID: W2789375724