Working Papers 2000 – Abstracts

7/2000

Bayesian Exponential Smoothing

Catherine S Forbes, Ralph D. Snyder and Roland G. Shami

In this paper, a Bayesian version of the exponential smoothing method of forecasting is proposed. The approach is based on a state space model containing only a single source of error for each time interval. This model allows us to improve current practices surrounding exponential smoothing by providing both point predictions and measures of the uncertainty surrounding them. We therefore propose a method for calculating prediction distributions via Monte Carlo composition. We evaluate the method with a Monte Carlo simulation study and then apply it to forecasting car part demand. The main advantage of the approach is that it produces exact, small sample prediction distributions. It also works very quickly on modern computing machines.

Keywords:  time series analysis, forecasting, structural model, local level model, prediction intervals

Next Abstract