Authorised by Academic Registrar, April 1996
Objectives On the completion of this subject students should be able to understand the nature of forecasts; recognise a time series data and principal components underlying it; select an appropriate forecasting technique; acquire skills to model a time series using a quantitative forecasting technique; evaluate competing forecasting models for performance; assess a situation requiring a qualitative forecasting technique; understand the limitations of a forecasting model; use a spreadsheet and a statistical package for modelling a time series; apply smoothing, decomposition, causal, ARIMA and some qualitative techniques for generating forecasts.
Synopsis The subject aims to introduce the art of forecasting via a modelling approach. The subject covers the nature and essentials of forecasting, introduction to time-series modelling, residual analysis; forecasting techniques - choice and applicability; causal techniques of forecasting, the moving average and exponential smoothing methods; the decomposition methods of forecasting, Delphi method, subjective probability method; technological forecasting techniques; an overview of advanced forecasting techniques - Box-Jenkins method, econometric models. Use of computer packages to compare forecasting techniques and to prepare forecasts.
Assessment Assignments: 60% + Examination: 40%