Keywords
S.E. of Regression
Akaike Information Criterion
Schwarz Information Criterion
Hannan-Quinn Information Criterion
Bivariate Regression models
Abstract
This study is on model selection in bivariate regression models. Data for this study were collected in CBN Annual Report (various issues), CBN Statistical bulletin (various issues)from 1990 to 2019, which consists of international oil prices (response variable) and unemployment rate (independent variable). Eight regression models; Linear Regression, Quadratic Regression, Cubic Regression, Power Regression, ab-Exponential Regression, Logarithmic Regression, Hyperbolic Regression and Exponential Regression were examined in this study. Five model selection techniques known as; coefficient of determination, standard error of Regression, Akaike Information Criterion, Schwarz Information Criterion, and Hannan-Quinn Information Criterion were used to select the best model. From the analysis, in the overall goodness of fit assessment, the study concluded that the ab- Exponential regression model with Exponential regression performs far better than the other six bivariate regression models employed in this study. Therefore, future researchers should look at a similar work by incorporating other nonlinear bivariate regression models like compound, growth and inverse Regression models to compare results.
References
doi:10.1109/TAC.1974.1100705, MR 042371
Aristizábal-Giraldo, E. V., Vélez-Upegui, J. I., and Martínez-Carvaja, H. E. (2016). A comparison of linear and nonlinear model performance of shia_landslide: a forecasting model for rainfall-induced landslides. Revista Facultad de Ingeniería, No. 80, pp. 74-88, 2016
Hamidian, H., Soltanian-Zadeh, H., Akhondi-Asl, A., Faraji-Dana, R. (2008). Comparison of Linear and Nonlinear Models for Estimating Brain Deformation Using Finite Element Method. In: Sarbazi-Azad H., Parhami B., Miremadi SG., Hessabi S. (eds) Advances in Computer Science and Engineering. CSICC 2008. Communications in Computer and Information Science, vol 6. Springer, Berlin, Heidelberg
Hannan, E. J., and Quinn, B. G. (1979). "The Determination of the order of an autoregression", Journal of the Royal Statistical Society, Series B, 41: 190–195.
Hunt, K. J. and Maurer, R.R. (2016). Comparison of linear and nonlinear feedback control of heart rate for treadmill running. Systems Science & Control Engineering, 4:1, 87-98, DOI: 10.1080/21642583.2016.1179139
Juliano, S. A., Williams, F.M. (1987). A comparison of methods for estimating the functional response parameters of the random predator equation. J Anim Ecol. 1987;56:641–653. doi: 10.2307/5074.
Magee L. (1990). R2 measures based on Wald and likelihood ratio joint significance tests. Amer Stat. 1990; 44:250–253. doi: 10.2307/2685352.
Montgomery, D.C., Peck, E.A., Vining, G.G. (2006). Introduction to Linear Regression Analysis. Wiley & Sons, Hoboken; 2006.
Nagelkerke, N.J.D. (1991). A note on a general definition of the coefficient of determination. Biometrika. 1991;78:691–692. doi: 10.1093/biomet/78.3.691.
Scarneciu, C.C., Sangeorzan, L., Rus, H., Scarneciu, V.D., Varciu, M.S. Andreescu, O. and Scarneciu, I. (2017). Comparison of Linear and Non-linear Regression Analysis to Determine Pulmonary Pressure in Hyperthyroidism. Pak J Med Sci. 2017 Jan-Feb; 33(1): 111–120.
Schwarz, G. (1978). Estimating the dimension of a model. The Annals of Statistics 6, 461-464
Spiess, A. and Neumeyer, N. (2010). An evaluation of R2 as an inadequate measure for nonlinear models in pharmacological and biochemical research: a Monte Carlo approach. BMC Pharmacol. V.10; 2010
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.