Quantitative Finance Stack Exchange is a question and answer site for finance professionals and academics. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I'm trying to figure out how to perform cointegration tests in R between 2 time series. I'm using po.test from the package tseries and ca.po and ca.jo from the package urca, and I have a couple of questions:

  • If I use PO which is non symmetric and one time series is stationary and the other isn't, I get opposite results. Is this normal? Also related I guess, if I have two time series and don't know yet whether they are stationary, can I use cointegration tests right away or do I need to pretest for unit roots?
  • When I use po.test and ca.po I get very different results, why is this?
share|improve this question
This may help. stats.stackexchange.com/questions/14615/… – vinux Apr 20 '13 at 3:13

I believe all you need to cope is:

share|improve this answer

the following link contains a very detailed and helpful tutorial about how to perform a cointegration test in R (i tried it myself and it works): www.fordham.edu/economics/vinod/R-chicken-eggs-coint.doc‎ in addition it answer your question about necessity of unite-root testing; good luck; Amer.

share|improve this answer
The link appears to be dead. – vanguard2k Jan 13 '14 at 7:51

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.