Premium
Forecasting Stock Index Futures Price Volatility: Linear vs. Nonlinear Models
Author(s) -
Najand Mohammad
Publication year - 2002
Publication title -
financial review
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.621
H-Index - 47
eISSN - 1540-6288
pISSN - 0732-8516
DOI - 10.1111/1540-6288.00006
Subject(s) - autoregressive conditional heteroskedasticity , stock index futures , volatility (finance) , econometrics , futures contract , autoregressive model , mean squared error , economics , nonlinear system , stock market index , index (typography) , linear model , stock (firearms) , mathematics , statistics , financial economics , stock market , computer science , geography , context (archaeology) , physics , archaeology , quantum mechanics , world wide web
The study examines the relative ability of various models to forecast daily stock index futures volatility. The forecasting models that are employed range from naïve models to the relatively complex ARCH‐class models. It is found that among linear models of stock index futures volatility, the autoregressive model ranks first using the RMSE and MAPE criteria. We also examine three nonlinear models. These models are GARCH‐M, EGARCH, and ESTAR. We find that nonlinear GARCH models dominate linear models utilizing the RMSE and the MAPE error statistics and EGARCH appears to be the best model for forecasting stock index futures price volatility.