Bayesian Forecasting Using Non-Linear Time Series Models

Abstract

It is generally considered that the 'statistical forecasting methods are .superiorto the methods, which are based on Non-statistical Principle. Non-statistical methods are less sophisticated and simple to understand for an ordinary person. 'This paper presents the forecast based on purely statistical methods called Bayesian Forecasting. Asymmetric time series method has been used along with Kalman Filter results. The GARCH process has been used to estimate non-constant variances in the observation equation and the system equation. Finally, exchange rate of Pakistani rupees against UK pounds is used for forecasting purposes.