An Innovative Financial Time Series Model: The Geometric Process Model
Geometric Process (GP) model is proposed as an alternative model for financial time series. The model contains two components: the mean of an underlying renewal process and the ratio which measures the direction and strength of the dynamic trend pattern over time. They simultaneously account for the uncertainty on the mean and the autoregressive and time-varying nature of the volatility. Compare to the popular GARCH and SV models, this model is simple and easy to implement using the least squares (LS) method.We extend the GP model to analyze the daily asset price range which exhibit threshold and asymmetric effects for some exogenous variables. Models are selected according to mean square error (MSE). Finally forecasting are performed for the best model that allows for both threshold and asymmetric effects.
KeywordsMean Square Error Severe Acute Respiratory Syndrome Stochastic Volatility GARCH Model Severe Acute Respiratory Syndrome
Unable to display preview. Download preview PDF.
- 15.Hull, J.C., White, A.: An analysis of the bias in option pricing caused by by a stochastic volatility. Advances in Futures and Options Research 3, 29–61 (1988)Google Scholar
- 19.Lam, Y.: The Geometric Process and it’s applications. World Scientific Publishing Co. Pte. Ltd. (2007)Google Scholar
- 22.Spiegelhalter, D., Thomas, A., Best, N.: Bayesian inference using Gibbs sampling for Window version (2000), The website for WinBUGS is http://www.mrc-bsu.cam.ac/bugs