Abstract:
ABSTRACT
This- study is based on nonlinear time series modelling in Nigeria. Two
models were considered. The first model adopted Gallant parametric model with
trigonometric transformation augmented with polynomial of order two, to address
the problem of missing values. This is called Augmented Nonlinear Parametric
Time Series Model (ANPTSM). In addition, the second model was formulated
using Ordinary Least Squares Method, trigonometric transformation and method
of calculating an expected value in contingency table of multivariate observations.
This is called Modifie~ Nonlinear Trigonometric Transformation Time Series
Model (MNTTSM) .
•
The ANPTSM IS a nonlinear parametric time senes model usmg
trigonometric transformation to solve the problem of missing values in time series,
while MNTTSM is a model for the conditional mean of modified nonlinear time
series. The consistency and efficiency of the models formulated were determined.
The study examined Nonlinear Trigonometric Transformation as well as
Augmented Nonlinear Trigonometric Transformation with polynomial of order
two. The two models were practically tested and compared using daily mean of
temperature for Ikeja, Ibadan, Ilorin, Minna and Zaria with different rates of
missing values. The results were used to determine the consistency and efficiency
of the models formulated which showed that MNTTTSM is able to address the
problem of missing values and forecast better than the ANPTSM.
