Q: 11
An ecommerce brand runs a multi-cell Conversion Lift test. The brand needs to determine if bidding in the Facebook auction based on user value calculated from its LTV model versus demographic targeting improves performance by 10%. The p-value for the test is calculated as p = 0.95. How should the analyst interpret bidding based on user value?
Options
Discussion
No, not C here. B fits since with p = 0.95, you can't claim a 10% effect from user value bidding.
Its B for sure. With that high p-value (0.95), there's no statistical significance-so you can't claim the 10% lift is due to bidding based on user value. Pretty sure stats rules back this up, but happy if anyone disagrees.
C/D? With a p-value that high (0.95), usually you can't say the lift is due to user value bidding, but if the brand only cares about observed change not significance there's a tiny argument for C. Lean B since exams stick to stats logic.
B is the right call. With p = 0.95, that's way above the usual significance threshold, so you can't say the 10% lift came from user value bidding. I think stats folks would agree, but open to other views.
I’m not sure it’s B, I think C fits if you just look at their reported lift and ignore the p-value trap.
Option C seen similar question in the official guide.
Probably B. With a p-value of 0.95, there's way too much chance involved to confidently link the 10% increase to user value bidding. Statistically, that's not significant. Pretty sure on this one but open to another viewpoint.
C
Its C, this feels right based on similar exam reports and the way the p-value is high here. Would double check with the official study guide or Facebook Blueprint docs just to be sure.
Be respectful. No spam.
