Welcome to the Q&A Forum

Thanks Keri.  Appreciate the offer, but I'm all set.  We just 301d the page after the test was done and have decided that we'll only multivariate the home page for now.  We've now had 3 major press links point to the testing version of our home page, so we've decided our best bet is just to set up all tests as multivariate so we don't create two different URLs.

Thanks again.

Thanks for your thoughts.

While a canonical shouldn't impact a split test, a 301 would create a loop and make an A/B test impossible.  Although, if we were to 301 this page, we wouldn't use that same page for testing.

As far as multivariate vs A/B.  The design changes are often significant enough where a multivariate is impossible.

FYI - we use Google Website Optimizer for our tests.

Thanks again.  Appreciate your weighing in.

To rel-canonical or to 301, that is the question.

We're frequently running an A/B split test on our home page to optimize conversion.  As a result about 10,000 backlinks to our homepage point to the B page.  (If we're running a test when a blog or newspaper checks us out, there's a 50% chance they're diverted to the B page. So when they copy our home page URL, they're unknowingly copying the B page link.)

We can't contact all of these sites and ask for them to change their links.  A lot of the links are from big organizations that aren't interested in tweaking the links of old articles.

So should we rel-canonical or 301 the B page?  We consistently use the same URL for our B page tests, so we'd only have to 'fix' one page.

Thanks in advance!