Abstract
The artificial neural network analysis has the advantage of being able to identify non-linear relationships between variables that is hard to be found in parametric research methods. On the other hands, this non-parametric black box methods have limitations to show the contribution of variables due to complexity of relations.
 In this study, a dummy artificial neural network analysis is attempted on the gravity model of panel data for Korea's exports, and the contribution of the variables are presented by Partial Dependence Plots methods.
 This results also show that the existence of a non-linear relationship that was hard to be captured by the previous parametric researches. Especially, the non-linearity contribution were found in GDP, per capita GDP and remoteness variables.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Korea Association for International Commerce and Information
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
