Heterosked. problems when estimating a VAR / VECM (Lead-Lag)

[AHS]

Hi,

I am experiencing problems when trying to investigate the lead-lag relationship between spot and futures prices and would very much appreciate your help.

I have three pairs of spot and futures series, and after employing the Johansen cointegration test I have found that the 1st pair have rank=1, while pair 2 and 3 have rank=2. When estimating "normal" VECM (1st pair) and VAR (pair 2 and 3) models I get clear indications of heteroskedasticity in the residuals. To my knowledge I have two possibilities when trying to remedy this;

1. I may estimate new models incorporating some form of the ARCH method. After studying some articles I have found that Lee's (1994) VECM-GARCH-X model specification should be employed for the 1st pair, while a VAR-GARCH-BEKK is sufficient for pair 2 and 3. I do however not know how to estimate the VECM-GARCH-X. I think I am able to estimate the VAR-GARCH-BEKK by high-lighting one pair of series and choosing Open -> As System. However, I am not able to conduct the lead-lag analysis (Granger Causality tests and impulse response analyses) which are available when using Open -> As VAR. In line with this I am therefore not able to investigate the lead-lag relationship for any of the series when trying to estimate new models.

2. Another way to solve the problem would be to use White's (1980?) heteroskedasticity consistent variance-covariance matrix, but I do not know how this works or how to incorporate it for a VAR or VECM. If this is possible I do however think that employing the "normal" VECM and VAR estimation method is sufficient. I may then use the Granger Causality tests and impulse response analyses which are available when choosing Open - > As VAR.

I have a few other statistical packages than EViews 6 on my computer, so if I have to use another program do not hesitate to tell me.
If I need to clearify the problem, please contact me.

I appriciate your help very much :)