Abstract—Forecasting future values of economic variables
are some of the most critical tasks of a country. Especially the
values related to foreign trade are to be forecasted efficiently
as the need for planning is great in this sector. The main
objective of this research paper is to select an appropriate
model for time series forecasting of total import (in taka crore)
of Bangladesh. The decision throughout this study is mainly
concerned with seasonal autoregressive integrated moving
average (SARIMA) model, Holt-Winters’ trend and seasonal
model with seasonality modeled additively and vector
autoregressive model with some other relevant variables. A
try was made to derive a unique and suitable forecasting
model of total import of Bangladesh that will help us to find
forecasts with minimum forecasting error.
Index Terms—Arima model, forecasting accuracy Holt
Winters’ trend and seasonality method, Out of sample
accuracy measurement.VAR model.
Tanvir Khan, MS Student, Institute of Statistical Research and
Training, University of Dhaka, Bangladesh (tkhan1@isrt.ac.bd).
[PDF]
Cite:Tanvir Khan, "Identifying an Appropriate Forecasting Model for Forecasting Total Import of Bangladesh," International Journal of Trade, Economics and Finance vol.2, no.3, pp. 242-246, 2011.