EViews.com

Hi, I've been running a Quandt-Andrews-Test to identify a structural break in my time series data. The test leads to a date which perfectly fits the economic background but is not very significant (p value is 0.187 for maximum wald statistic and 0.21 for exp wald statistic). But when I take the breakpoint and run a chow test I get a good significant result.
So, my first question: Is this a common result if both test are combined?
And: Is it statistically feasible to take the not significant result of the QA-test and use it for chow's?

Thanks in advance for your help!

The first thing you should do is make sure your copy of EViews is up to date - the Quandt-Andrews test has had some revisions to it.

I'm using a computer at my university, it's runnning eviews6. I don't know if there are any updates for the Andrew-Quandt and if i could install them on the university's computer but I wil check.