Granger_cause rank deficiency problem

Dear All, I have return data on some N companies. I run pairwaise granger causality tests using granger_cause but matlab returns "A is rank deficient to within machine precision" for pretty much any regression. I GARCH(1,1) detrended my returns (so it is not a stationarity problem I would assume). Did anyone run into a similar problem before?

I am using: http://www.mathworks.com/matlabcentral/fileexchange/25467-granger-causality-test

Thanks in advance!

[John D'Errico]

Since we do not see your data, how can we know what is wrong with the data? The crystal ball is so foggy today. It just keeps on telling me the answer is 42, but nothing more.