This paper examines the lead-lag relationship between the spot index a
nd futures price of the Nikkei Stock Average. Using daily data in the
postcrash period we investigate the interaction between the spot and f
utures series through the error correction model. Two versions of erro
r correction models are considered, depending on the postulated long-r
un equilibrium relationship. It is found that lagged changes in the fu
tures price affect the short-term adjustment in the spot index, but no
t vice versa. Forecasting models for the spot index are also construct
ed using the univariate time series approach and the vector autoregres
sive method. For the post-sample forecast comparison the error correct
ion models produce the best results. The vector autoregressive method
performs better than the martingale model, while the univariate time s
eries method gives the poorest forecasts.