Comparative Analysis of Transformation Techniques to Reduce Multi-Collinearity Using Real GDP of Some Transport Variables that Contributes to Economic Growth in Nigeria

Main Article Content

Osunronbi Fatai Alani

Abstract

This study was carried out to compare transformation techniques of reducing multi-collinearity in linear regression using real GDP of some transport variables that contributes to economic growth in Nigeria from 1991-2020. The multiple regression model was used to establish the mathematical relationship between real GDP as the dependent variable and road transport, rail and pipeline transport, water transport, air transport and post and courier service as independent variables. In this work, regression was carried out on the original data to compare the number of independent variables significant with the same data for which the presence of multi-collinearity was reduced using inverse transformation and regression repeated. The results showed that; for original data 1 variable is significant, R2 = 93% and the number of independent variables with high VIF that is above 10 are two (road transport and water transport). Furthermore, the result for the reduce multi-collinearity inverse transformation reviewed that 5 variables were significant, R2 =95.2% and the number of independent with high VIF that is above 10 is three (road transport, air transport and post and courier service). Conclusively, the result from inverse transformation gives the best, using R2 and significant variables as basis for comparison. However useful recommendation was given based on the findings.

Keywords: Multi-Collinearity, GDP, Variance Inflation Factors (VIF), Transport, Economic Growth

Article Details

Comparative Analysis of Transformation Techniques to Reduce Multi-Collinearity Using Real GDP of Some Transport Variables that Contributes to Economic Growth in Nigeria. (2024). African Journal of Advances in Science and Technology Research, 14(1), 1-15. https://doi.org/10.62154/j74h3q95
Articles

Copyright (c) 2024 Osunronbi Fatai Alani (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.