This course provides part of the essential knowledge and skills required for conducting the Final Project module in the final year.
Forecasting is the process of making statements about events whose actual outcomes (typically) have not yet been observed. A commonplace example might be estimation of some variable of interest at some specified future date. This module gives you a thorough understanding of various statistical methods for forecasting, in particular time-series methods that have wide applications in business.
Risk and uncertainty are central to forecasting and prediction; it is generally considered good practice to indicate the degree of uncertainty attaching to forecasts, and sometimes it is necessary to provide distributional rather than point forecasts. As such, an introduction to methods for distributional forecasting will also be provided.
As forecasting often requires huge amount of data, both for training and testing the models, and the required formulae and equations are often complicated, it is essential to implement forecasting methods using a proper statistical package. As such training will be provided on using R and SAS package for implementing forecasting methods.