Modeling Domestic Output from Selected Macroeconomic Variables in Nigeria Using Cross-Validated Scatterplot Smoothers

Are, S.O and Alabi, N. O. (2016) Modeling Domestic Output from Selected Macroeconomic Variables in Nigeria Using Cross-Validated Scatterplot Smoothers. In: Academic Staff Union of Polytechnics (ASUP) Ilaro Chapter 5th National Conference, 2016, The Federal Polytechnic, Ilaro.

[img] Text
Conference 7_Alabi NO.pdf

Download (1MB)

Abstract

We employed generalized additive models (GAMs) with scatterplot smoothers such as cubic smoothing splines and local regression to establish non-linear relationships that exist between Nigeria’s domestic output proxy by gross domestic products and four macroeconomic variables such as recurrent and capital expenditures, crude oil prices and federal government retained earnings. Four flexible generalized additive models were postulated. These are smoothing splines, local regression, local quadratic regression and composite GAM. Generalized Cross-validation and leave-one-out re-sampling techniques were employed in determining the effective degrees of freedom and the window size or span for smooth splines and local regression additive models respectively. We compared models accuracy using the residual deviance for the GAMs. Smoothing Splines was selected through a nested analysis of deviance on the four postulated models. The minimized penalized residual sum of squares optimal tuning parameters Ω = 1.2613x10-6, 2.0153x10-6, 7.9291x10-7 and 1.5286x10-7 for each smoothing functions on federal government retained earnings, crude oil prices, recurrent expenditure and capital expenditure respectively which control the tradeoff between goodness-of-fit and smoothness of the smoothing spline model. Analysis shows the federal government retained earnings and volatile crude oil prices are the major macroeconomic variables that cause instability in the growth of gross domestic products in Nigeria. R programming language packages such as “splines”,“gam”,“ggplot2”,“boot”and“lattice” amongst others were employed throughout the analysis.

Item Type: Conference or Workshop Item (Paper)
Subjects: Q Science > Q Science (General)
Q Science > QA Mathematics
Divisions: Faculty of Engineering, Science and Mathematics > School of Mathematics
Depositing User: Mr Taiwo Egbeyemi
Date Deposited: 09 Jun 2020 16:17
Last Modified: 09 Jun 2020 16:17
URI: http://eprints.federalpolyilaro.edu.ng/id/eprint/389

Actions (login required)

View Item View Item