Forecasting Realized Volatility with Linear and Nonlinear Models
In this paper we consider a nonlinear model based on neural networks as well as linear models to forecast the daily volatility of the S&P 500 and FTSE 100 indexes. As a proxy for daily volatility, we consider a consistent and unbiased estimator of the integrated volatility that is computed from high frequency intra-day returns. We also consider a simple algorithm based on bagging (bootstrap aggregation) in order to specify the models analyzed in the paper.
|Keywords||bagging, financial econometrics, neural networks, nonlinear models, realized volatility, volatility forecasting|
|JEL||Time-Series Models; Dynamic Quantile Regressions (jel C22), Forecasting and Other Model Applications (jel C53), Asset Pricing (jel G12), Financial Forecasting (jel G17)|
|Publisher||Erasmus School of Economics|
|Series||Econometric Institute Research Papers|
|Journal||Report / Econometric Institute, Erasmus University Rotterdam|
McAleer, M.J, & Medeiros, M.C. (2009). Forecasting Realized Volatility with Linear and Nonlinear Models (No. EI 2009-37). Report / Econometric Institute, Erasmus University Rotterdam (pp. 1–26). Erasmus School of Economics. Retrieved from http://hdl.handle.net/1765/17303