Determinants of Efficacy of Studying in the Republic Croatia - Comparing Neural Networks and Decision Trees: Research Framework Proposition

Konferenzbeitrag

Rapid technological development and progress lead to the need for better and more efficient education which should prepare the applicant for increasingly flexible labour market. The goal of this research is to create models for prediction of student's efficacy, compare them, find the key factors that contribute to more efficient studying in the Republic of Croatia, and finally determine how efficient studying is related to first employment. Models will be based on students' data and hypothesis will be tested using multivariate statistical methods (multiple regressions, Cronbach's alpha), decision trees and neural networks. Data will be collected by structured questionnaire and will consist of demographic and economic data, information about previous education, attitudes towards learning, and goals after completing studies and information about the first employment. Students' efficacy will be measured by grade point average in college. This research will try to increase our understanding of how different factors influence students' performance and how students' efficacy affects the speed and conditions of finding the first employment.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: In: Proceedings of the ENTRENOVA - ENTerprise REsearch InNOVAtion Conference, Rovinj, Croatia, 8-9 September 2016 ; Year: 2016 ; Pages: 123-129 ; Zagreb: IRENET - Society for Advancing Innovation and Research in Economy

Classification and Topics

• Classification: Wirtschaft ; Higher Education; Research Institutions ; Neural Networks and Related Topics
• Subject: efficacy of studying ; education ; neural network ; decision trees

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Bilal Zorić, Alisa
• Event: Veröffentlichung
• (who): IRENET - Society for Advancing Innovation and Research in Economy
• (where): Zagreb
• (when): 2016

Further information

• Handle: http://hdl.handle.net/10419/183708
• Last update: 10.03.2025, 11:42 AM CET