Hi friends, I would really appreciate if somebody helps me give
better understanding on subject matter.
Suppose I have a set of Integrated variables (say max order is 1). I understand
there may be some cases when there could be some linear combinations which are
stationary and this phenomena is called as co-integration.
Now suppose I have a vector of Random walks (which is also integrated of order
1 each), where error terms are not necessarily independent but of
course uncorrelated over time i.e. error terms are WN. Here my question is
still can we find some linear combinations (like co-integrated variables) which
are stationary? And if not, why this is not.
Please forgive me if my question seems very naive. However
although intuitively I feel that no such linear relationships exist for RWs,
however I find hard to explain to 2nd person.
Any help please?
Thanks
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
