R help - Jun 2007 - Question regarding Johansen's cointegration testing

Hi,

I have a couple of questions about johansen's test, in general:

1. I was able to obtain error correction term (ect) from cajorls$rlm$model
properly. According the my ca.jo object on 2-variate series, the test suggests
that the integration rank is 1. Which means that my ect should be stationary.
However, I did test stationariy on ect and it shows non-stationarity and my acf
still shows high and long autocorrelation. How should I interpret the result
from Johansen then?

2. In some cases for 2-variate series, I found that Johansen testing shows that
my test statistics are lower than the 5% for both r <= 0 and r <= 1. That
means I have 1 or 0 cointegration relationship? How should I interpret this
result?

Thank you,

- adschai

	[[alternative HTML version deleted]]