Practical Comparison of Results of Statistic Regression Analysis and Neural Network Regression Analysis

Marek Vochozka

Littera Scripta, 2016, vol. 9, issue 2

Abstract: There are many discussions and arguments about accuracy of the results of statistic regression analysis and neural network regression analysis among experts. Of course all of them look for the best method usable in practice. The objective of the contribution is to use a case study to answer the question which of the methods provides better results. As a case study will be used time series of US Gross Domestic Product. It starts in 1966 and ends in 2014. The future development of the variable for the following 20 years will be calculated. Software Statistica 12 developed by Dell corporation will be used for both analyses. The first one will use multiple regression of the software. The second one will use data mining section with its neural networks. Generalized Regression Neural Networks, Multi-layer Perceptron Network, Radial Basis Function Neural Networks, Linear Neural Networks will by calculated. The results are two curves, the first based on statistic regression analysis. The second curve is provided by the best model of neural networks. Both the curves will describe development of the US GDP in 20 next years.

Keywords: regression analysis; neural network; gross domestic product; statistic regression (search for similar items in EconPapers)
Date: 2016
References: Add references at CitEc
Citations:

Downloads: (external link)
https://littera-scripta.com/articles/practical-com ... neural-netw-263b61d2 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rsg:littra:2016-023

Access Statistics for this article

More articles in Littera Scripta from VSTE
Bibliographic data for series maintained by Robin Kunju Mol Raj ().