<t>QuoteOriginally posted by: crowlogicCan you expand a bit on SIC? The code I have only uses AIC or BIC.. and what information I can find sometimes calls BIC "SBIC".Also, re: Stochastic structural breaks. I don't think that is needed here, when estimating intraday conintegration the breaks are dete...

<t>QuoteOriginally posted by: crowlogicJohansen.. one curious result is that I am getting quite large differences of the optimal lag whether I use AIC or BIC to select it. AIC always seems to select a lag roughly twice as long as BIC.QuoteOriginally posted by: DogonMatrixI am working on exactly the ...

I am working on exactly the same problem. I think concatenate is not such a good idea. Which cointegration method are you using ? Engle-Granger or Johansen ?

I think that's Dornbush(1976)

anybody would have the code for that ?Thanks

looking for stronger theoretical background , may be you will find usefull to look at the garch(1,1) representation of the Ewma.

<t>QuoteOriginally posted by: PanniniCould you please recommend any references (other than Vidyamurthy) which explain why conintegration should be adopted and correlation abandoned? I had a lot of difficulty trying to convince my manager that market situations can commonly arise where correlation br...

<t>There are different ways to test for cointegration: one could be the Johansen approach using eigenvalues, another one could be the Engle-Granger approach using Augmented DF on the residuals. It is conceivable that you could run first a Johansen test of cointegration ( which has some good properti...

Will you go as far as telling us the name of your system so we can follow how well you are doing ?

may be you should try these :www.collective2.comwww.striker.comwww.attaincapital.com

In the spirit of the original post.What is the state of the electricity trading in the US ?Is it for the most part dead ? Or is it a real trading market ?

is this really new ? I think people have been talking about GA for a while.

thanks

Will anybody have a good reference on the application of either Cholesky or Single Value Decomposition for VAR ( as in Vector Autoregression) ?

There are also some approaches based on maximum entropy.But how do you solve the data quality problem in commodity options ? the more sophisticated the approach the more reliant you are on having clean data, I think.