search

wbnicholson / BigVAR

Dimension Reduction Methods for Multivariate Time Series
56 stars 17 forks source link

The script can run without stop. #6

Open weiweilars opened 6 years ago

weiweilars commented 6 years ago

For some data (I think the magnitude of the data are huge), the cv.BigVAR function can run without stop. How I can resolve this problem? Thanks for help!

wbnicholson commented 6 years ago

What are the dimensions of your problem and what structures are you using? You could consider increasing the optimization tolerance via the argument "tol" in constructModel. By default it is set to 1e-4, but for larger problems it could be set to 1e-3 without much loss in precision.