NEW FRONTIERS FOR ARCH MODELS Prepared for Conference on Volatility Modeling and Forecasting Perth, Australia, September 2001 Robert Engle UCSD and NYU
The First ARCH Model Rolling Volatility or “Historical” Volatility Estimator – Weights are equal for j<N – Weights are zero for j>N – What is N?
1982 ARCH Paper Weights can be estimated ARCH(p)
WHAT ABOUT HETEROSKEDASTICITY?
EXPONENTIAL SMOOTHER Another Simple Model – Weights are declining – No finite cutoff – What is lambda? (Riskmetrics=.06)
The GARCH Model The variance of r t is a weighted average of three components – a constant or unconditional variance – yesterday’s forecast – yesterday’s news
FORECASTING WITH GARCH GARCH(1,1) can be written as ARMA(1,1) The autoregressive coefficient is The moving average coefficient is
GARCH(1,1) Forecasts
Monotonic Term Structure of Volatility
FORECASTING AVERAGE VOLATILITY Annualized Vol=square root of 252 times the average daily standard deviation Assume that returns are uncorrelated.
TWO YEARS TERM STRUCTURE OF PORT
Variance Targeting Rewriting the GARCH model where is easily seen to be the unconditional or long run variance this parameter can be constrained to be equal to some number such as the sample variance. MLE only estimates the dynamics
The Component Model Engle and Lee(1999) q is long run component and (h-q) is transitory volatility mean reverts to a slowly moving long run component
MORE GARCH MODELS CONSIDER ONLY SYMMETRIC GARCH MODELS ESTIMATE ALL MODELS WITH A DECADE OF SP500 ENDING AUG GARCH(1,1), EGARCH(1,1), COMPONENT GARCH(1,1) ARE FAMILIAR
OLDER GARCH MODELS Bollerslev-Engle(1986) Power GARCH omega alpha p beta Log likelihood
PARCH Ding Granger Engle(1993) omega alpha gamma beta Log likelihood
TAYLOR-SCHWERT Standard deviation model omega alpha beta Log likelihood
SQ-GARCH MODEL SQGARCH (Engle and Ishida(2001)) has the property that the variance of the variance is linear in the variance. They establish conditions for positive and stationary variances
SQGARCH LogL: SQGARCH Method: Maximum Likelihood (Marquardt) Date: 08/03/01 Time: 19:47 Sample: Included observations: 2927 Evaluation order: By observation Convergence achieved after 12 iterations Coefficient Std. Errorz-StatisticProb. C(1) C(2) C(3) Log likelihood Akaike info criterion Avg. log likelihood Schwarz criterion Number of Coefs.3 Hannan-Quinn criter
CEV-GARCH MODEL The elasticity of conditional variance with respect to conditional variance is a parameter to be estimated. Slight adjustment is needed to ensure positive variance forecasts.
NON LINEAR GARCH THE MODEL IS IGARCH WITHOUT INTERCEPT. HOWEVER, FOR SMALL VARIANCES, IT IS NONLINEAR AND CANNOT IMPLODE FOR
NLGARCH LogL: NLGARCH Method: Maximum Likelihood (Marquardt) Date: 08/18/01 Time: 11:27 Initial Values: C(2)= , C(4)= , C(1)= Convergence achieved after 32 iterations CoefficientStd. Errorz-StatisticProb. alpha gamma delta Log likelihood Akaike info criterion Avg. log likelihood Schwarz criterion Number of Coefs.3 Hannan-Quinn criter
Asymmetric Models - The Leverage Effect Engle and Ng(1993) following Nelson(1989) News Impact Curve relates today’s returns to tomorrows volatility Define d as a dummy variable which is 1 for down days
NEWS IMPACT CURVE
Other Asymmetric Models
PARTIALLY NON-PARAMETRIC ENGLE AND NG(1993)
EXOGENOUS VARIABLES IN A GARCH MODEL Include predetermined variables into the variance equation Easy to estimate and forecast one step Multi-step forecasting is difficult Timing may not be right
EXAMPLES Non-linear effects Deterministic Effects News from other markets – Heat waves vs. Meteor Showers – Other assets – Implied Volatilities – Index volatility MacroVariables or Events
STOCHASTIC VOLATILITY MODELS Easy to simulate models Easy to calculate realized volatility Difficult to summarize past information set How to define innovation
SV MODELS Taylor(1982) beta=.997 kappa=.055 Mu=0
Long Memory SV Breidt et al, Hurvich and Deo d=.47 kappa=.6
Breaking Volatility Randomly arriving breaks in volatility mu=-0.5 kappa=1 p=.99