Modelling conditional heteroskedasticity: Application to stock return lndex "IBEX-35

This paper compares alternative time-varying volatility models for daily stock-returns using data from Spanish equity index IBEX-35. Specifically, we have estimated a parametric family of models of generalized autoregressive heteroskedasticity (which nests the most popular symmetric and asymmetric GARCH models, a semiparametric GARCH model, the stochastic volatility model SV(l), the Poisson jump diffusion process and finally, a non-parametric mode!. We obtain that those models which use conditional standard deviation produce better fits than all other GARCH models. We also compare all models using a standard efficiency test (which compares within sample predictive power and conclude that general GARCH models (specifically the TGARCH(1,ll model perform better than all others.