TRANSFER FUNCTION MODELLING OF INFLATION RATE AND IMPORT DUTIES IN NIGERIA

Abstract

The goal of this investigation is to use transfer function to model Nigeria's inflation rate and import duties. The two series were collected from the website of Nigeria's Central Bank (for 16 years). The data were checked for stationarity using appropriate transformations at first. The ARIMA (p d q), was used to estimate five models for the input series. The best model was selected based on the minimum information criterion. As a result, the input series was modelled using ARIMA (1,1,0) autoregressive integrated moving average models. The  input and output variable was  pre whitened. The analysis of  cross-correlation function  was used to provide a rational for the polynomial representation of the dynamic transfer function models. It was discovered that the calculated noise was autocorrelated. This filled in the gaps in the transfer function model, which was then used to fit the whole thing together. The resulting model was put through a diagnostic test and found to be suitable. As a result, a forecast was made.